© 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. 4-CLT-HP
    7. 1039
    Prev
    Next
    INDEX
    Explanations

    Degree/Amount

    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
     keç
    -0.54
     ferons
    -0.54
     recommandons
    -0.54
     marquis
    -0.52
    skyl
    -0.52
    StructEnd
    -0.52
     âgé
    -0.51
     rappresent
    -0.51
     pronti
    -0.51
     herinner
    -0.51
    POSITIVE LOGITS
    findpost
    0.80
    DockStyle
    0.73
    /*
    0.68
     validating
    0.56
    ContentAsync
    0.56
     sad
    0.55
     <<<<<<<<<<<<<<
    0.55
     ModelExpression
    0.55
     Himo
    0.53
    saraba
    0.52
    Activations Density 0.007%

    No Known Activations