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

    Neuronpedia

    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. 13243
    Prev
    Next
    INDEX
    Explanations

    phrases expressing likelihood or probability

    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
    1325
    +0.11
    0.4%
    1392
    +0.11
    0.4%
    812
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.11
    0.03
    1392
    +0.11
    0.03
    168
    +0.11
    0.03
    Negative Logits
    aut
    -0.43
    Revenir
    -0.42
     Wol
    -0.42
     Sem
    -0.41
    Bois
    -0.41
    Schwar
    -0.41
     Gelen
    -0.41
    Sem
    -0.41
    nová
    -0.40
    commun
    -0.39
    POSITIVE LOGITS
     Likely
    0.89
    Likely
    0.88
    likely
    0.86
     likely
    0.84
     NTIS
    0.63
    unlikely
    0.63
     Likelihood
    0.62
     tramont
    0.61
     boulangerie
    0.59
     likelihood
    0.59
    Activations Density 0.090%

    No Known Activations