© 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. 4-CLT-HP
    7. 282
    Prev
    Next
    INDEX
    Explanations

    fisherman

    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
    RegressionTest
    -0.65
     للاسماء
    -0.64
    DockStyle
    -0.63
    קישורים
    -0.57
     gynhyrchwyd
    -0.53
    出版年
    -0.53
    허
    -0.52
    WebElementEntity
    -0.51
    İstinadlar
    -0.50
    ftagPool
    -0.50
    POSITIVE LOGITS
     friends
    0.51
    ]--;
    0.49
    principalTable
    0.49
    Moc
    0.47
     roles
    0.47
    Ặ
    0.47
     pole
    0.47
     chiefs
    0.46
    thermia
    0.46
    tonode
    0.46
    Activations Density 0.003%

    No Known Activations