© 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. 5-CLT-HP
    7. 5520
    Prev
    Next
    INDEX
    Explanations

    and

    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
     BoxFit
    -0.80
    RenderAtEndOf
    -0.78
     ComVisible
    -0.75
     more
    -0.74
     Réponses
    -0.70
     invariably
    -0.69
     AppBundle
    -0.69
     even
    -0.69
    __':
    -0.68
    __":
    -0.68
    POSITIVE LOGITS
    /
    0.45
     to
    0.43
     like
    0.42
     I
    0.41
     t
    0.41
    UEL
    0.37
     (
    0.36
    +#+
    0.36
    Centre
    0.35
    FLP
    0.35
    Activations Density 0.000%

    No Known Activations