© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 94743
    Prev
    Next
    INDEX
    Explanations

    than

    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
    tagHelperRunner
    -1.11
    MigrationBuilder
    -1.10
     betweenstory
    -1.08
     itſelf
    -1.04
    ########.
    -1.01
    StoryboardSegue
    -1.00
     Савезне
    -0.97
     myſelf
    -0.96
     ModelExpression
    -0.96
     doubtnut
    -0.96
    POSITIVE LOGITS
     
    0.63
     or
    0.60
     with
    0.58
     A
    0.57
     C
    0.56
     T
    0.55
     are
    0.55
     <
    0.55
     for
    0.54
     H
    0.54
    Activations Density 0.397%

    No Known Activations