© 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. 94850
    Prev
    Next
    INDEX
    Explanations

    Russ

    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
     Russ
    -0.85
    Russ
    -0.80
    taminophen
    -0.63
    standers
    -0.62
    kina
    -0.61
    ritt
    -0.57
     فريبيس
    -0.57
    AnchorStyles
    -0.55
    Expedia
    -0.55
     Monfieur
    -0.54
    POSITIVE LOGITS
    最快更新
    0.63
    oman
    0.54
    ArgsConstructor
    0.53
     Con
    0.51
    maxcdn
    0.51
     bot
    0.49
     leaders
    0.49
    lyl
    0.49
    ancien
    0.49
    WriteLiteral
    0.48
    Activations Density 1.661%

    No Known Activations