© 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. Gemma-2-2B
    5. 5-CLT-HP
    7. 3669
    Prev
    Next
    INDEX
    Explanations

    mental

    np_max-act · gemini-2.0-flash
    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
    ="#"><
    -0.58
    errHandler
    -0.56
    BagConstraints
    -0.56
    )_/¯
    -0.56
    ěry
    -0.52
    <()>
    -0.52
    <?,
    -0.49
    FirstResponder
    -0.49
    MLLoader
    -0.48
    didReceive
    -0.47
    POSITIVE LOGITS
    ftagPool
    0.86
    IsMutable
    0.71
     or
    0.57
    Personensuche
    0.57
     cerveau
    0.56
     mental
    0.55
     ProtoMessage
    0.54
    <bos>
    0.54
    UserList
    0.52
     sanitaire
    0.52
    Activations Density 0.002%

    No Known Activations