© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 46085
    Prev
    Next
    INDEX
    Explanations

    New York City

    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
    MigrationBuilder
    -0.67
     quæ
    -0.57
    tvguidetime
    -0.52
    tagHelperRunner
    -0.50
    charpe
    -0.49
    TargetException
    -0.46
    //
    -0.45
    ījum
    -0.44
    StoryboardSegue
    -0.44
    /*
    -0.43
    POSITIVE LOGITS
    onActivityResult
    0.65
    reactstrap
    0.60
    TAWA
    0.56
     dedans
    0.56
     >=",
    0.56
    écial
    0.56
    providedIn
    0.56
    RenderAtEndOf
    0.55
     getItemId
    0.55
     Exactos
    0.54
    Activations Density 0.063%

    No Known Activations