© 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. 0-CLT-HP
    7. 95207
    Prev
    Next
    INDEX
    Explanations

    gger

    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
    gger
    -2.36
    migrationBuilder
    -0.63
    ggers
    -0.62
     continúas
    -0.59
    脚注の使い方
    -0.58
    AndEndTag
    -0.58
    gili
    -0.57
    ggar
    -0.55
     AssemblyCompany
    -0.53
    twimg
    -0.52
    POSITIVE LOGITS
    tellungs
    0.65
     fusca
    0.58
     Haarlem
    0.57
     ―――――
    0.56
    </tfoot>
    0.56
    pidou
    0.56
     Efq
    0.55
    newInstance
    0.55
     ſeveral
    0.55
     Loire
    0.54
    Activations Density 0.317%

    No Known Activations