© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5422
    Prev
    Next
    INDEX
    Explanations

    phrases related to confidence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1363
    +0.14
    0.5%
    1527
    +0.14
    0.5%
    1194
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1490
    +0.14
    0.03
    1194
    +0.14
    0.02
    1053
    +0.14
    0.03
    Negative Logits
     unspeak
    -0.82
     viciss
    -0.82
     inconce
    -0.77
     indestru
    -0.77
     Leurs
    -0.76
     reluct
    -0.76
     disagre
    -0.75
     hcm
    -0.73
     nomine
    -0.73
     indescri
    -0.73
    POSITIVE LOGITS
     confidence
    1.39
     Confidence
    1.32
    confidence
    1.29
    Confidence
    1.16
     confident
    1.15
    confident
    1.02
     confidently
    0.88
     CONF
    0.86
     conf
    0.78
     confianza
    0.72
    Activations Density 0.075%

    No Known Activations