© 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. 5076
    Prev
    Next
    INDEX
    Explanations

    hasn't

    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
    findpost
    -0.69
    ConstraintMaker
    -0.69
    ApiModelProperty
    -0.65
    makeConstraints
    -0.63
    GEBURTSDATUM
    -0.63
     &___
    -0.59
    ləş
    -0.57
    MigrationBuilder
    -0.56
     jspb
    -0.53
    Datuak
    -0.52
    POSITIVE LOGITS
     تانيه
    0.55
    GHIJKLM
    0.49
     estimate
    0.49
    Katso
    0.47
    Fic
    0.47
     experience
    0.47
     للاسماء
    0.46
    cshtml
    0.46
    expandindo
    0.46
     notice
    0.46
    Activations Density 0.001%

    No Known Activations