© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2911
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.75
     getItemCount
    -0.60
    BagConstraints
    -0.59
    ledem
    -0.57
    ibilité
    -0.57
     qualify
    -0.57
     belong
    -0.57
    показания
    -0.56
     expand
    -0.56
     enable
    -0.56
    POSITIVE LOGITS
    LookAnd
    0.63
     Lightboxes
    0.57
    ThroughAttribute
    0.53
     udaler
    0.50
    messageInfo
    0.48
    ⓧ
    0.48
     dressing
    0.47
    typeorm
    0.47
     complaining
    0.46
    bitField
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.