© 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. 1-CLT-HP
    7. 13938
    Prev
    Next
    INDEX
    Explanations

    adding

    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
     added
    -0.97
     add
    -0.88
     Add
    -0.81
     addition
    -0.80
     adding
    -0.79
    added
    -0.78
    Add
    -0.78
     Added
    -0.77
     adds
    -0.74
    Added
    -0.72
    POSITIVE LOGITS
    DeleteBehavior
    0.73
    djangoproject
    0.68
    ActionCreators
    0.67
     FBref
    0.67
    riwal
    0.66
     BoxFit
    0.65
     CascadeType
    0.65
    migrationBuilder
    0.65
    URLException
    0.65
    jooq
    0.63
    Activations Density 0.007%

    No Known Activations