© 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. 5272
    Prev
    Next
    INDEX
    Explanations

    -

    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
    <bos>
    -0.67
    دانشنامهٔ
    -0.59
    AndEndTag
    -0.56
    MigrationBuilder
    -0.56
     препратки
    -0.55
     esternos
    -0.53
    oredCriteria
    -0.52
     ویکی‌آمباردا
    -0.52
     splen
    -0.50
    rrggbb
    -0.49
    POSITIVE LOGITS
    andExpect
    0.49
     all
    0.49
    ță
    0.49
    ungkinkan
    0.48
    zeitig
    0.47
    ษัท
    0.47
    tagext
    0.47
     threat
    0.47
    utoff
    0.47
     danger
    0.46
    Activations Density 0.023%

    No Known Activations