© 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. 946
    Prev
    Next
    INDEX
    Explanations

    explanations, reasons, causes

    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
     continúas
    -0.66
    '&:
    -0.60
    findpost
    -0.57
    EnableWeb
    -0.55
     disambiguazione
    -0.54
    }]);
    -0.54
     ['./
    -0.53
    WebElementEntity
    -0.52
    }`)
    -0.51
    IEWS
    -0.50
    POSITIVE LOGITS
     because
    0.70
     when
    0.56
     owing
    0.49
     оригіналу
    0.48
     потому
    0.47
    CloseOperation
    0.47
     in
    0.47
     a
    0.47
    because
    0.46
     parce
    0.45
    Activations Density 0.007%

    No Known Activations