© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14395
    Prev
    Next
    INDEX
    Explanations

    intelligence

    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
    awtextra
    -0.56
     interchange
    -0.51
    енча
    -0.49
     Gaulle
    -0.45
    IsInitialized
    -0.44
    InvalidProtocol
    -0.44
     intelligence
    -0.44
     IQ
    -0.43
     Concorde
    -0.43
     hood
    -0.41
    POSITIVE LOGITS
     igång
    0.59
    DockStyle
    0.58
    borgen
    0.56
     sélectionnez
    0.56
    SerializedName
    0.56
     prochaines
    0.56
     ویکی‌پدیا
    0.54
     visibilité
    0.54
    InjectMocks
    0.54
     stabilité
    0.54
    Activations Density 0.075%

    No Known Activations