© 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. 5577
    Prev
    Next
    INDEX
    Explanations

    words related to certifications or guarantees

    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
    172
    +0.16
    0.7%
    893
    +0.15
    0.7%
    555
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.16
    0.02
    893
    +0.15
    0.02
    1527
    +0.14
    0.02
    Negative Logits
    xions
    -0.50
    lüğü
    -0.50
    Treas
    -0.50
    uckoo
    -0.46
    Referencie
    -0.45
    ztés
    -0.45
     Guido
    -0.44
    optString
    -0.43
    řevě
    -0.43
    styleUrls
    -0.42
    POSITIVE LOGITS
     cer
    1.30
     Cer
    1.27
    Cer
    1.18
     certification
    1.16
     certify
    1.09
     CERT
    1.09
     certificate
    1.07
     Certification
    1.07
     certificates
    1.07
     certifications
    1.06
    Activations Density 0.112%

    No Known Activations