© 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. 5-CLT-HP
    7. 97778
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    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
     -
    -0.79
    LookAnd
    -0.76
    SourceChecksum
    -0.69
    InitVars
    -0.64
    migrationBuilder
    -0.60
    fillType
    -0.58
    ----------------
    -0.57
     '-
    -0.56
     -'
    -0.56
    ThroughAttribute
    -0.56
    POSITIVE LOGITS
     Soledad
    0.48
     cref
    0.48
     Cristóbal
    0.45
     quarterfinals
    0.45
     nervosa
    0.44
     bribery
    0.43
     Aimee
    0.43
     scaffold
    0.43
     multiverse
    0.43
     soldering
    0.43
    Activations Density 0.001%

    No Known Activations