© 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. 14798
    Prev
    Next
    INDEX
    Explanations

    dep

    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
    }))
    -0.82
    BASEPATH
    -0.78
    Rhestr
    -0.78
    CopyWith
    -0.74
    Hochspringen
    -0.73
    
    -0.70
    MigrationBuilder
    -0.70
    ThroughAttribute
    -0.69
     protoimpl
    -0.69
     ProtoMessage
    -0.68
    POSITIVE LOGITS
    buck
    0.53
    mer
    0.46
    IDENTAL
    0.45
    BUCK
    0.43
    itag
    0.43
     such
    0.42
    ugin
    0.42
    XtraGrid
    0.42
    interface
    0.41
    met
    0.41
    Activations Density 0.028%

    No Known Activations