© 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. 91927
    Prev
    Next
    INDEX
    Explanations

    import

    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
     ModelExpression
    -0.85
    ]")]
    -0.80
     '\\;'
    -0.78
    UnsafeEnabled
    -0.78
    HtmlAttribute
    -0.77
     snippetHide
    -0.77
    uxxxx
    -0.76
    #+#
    -0.74
    archiviato
    -0.73
    awtextra
    -0.72
    POSITIVE LOGITS
    kust
    0.54
    TERY
    0.52
    sly
    0.50
    員
    0.47
    yse
    0.47
     Logan
    0.46
    員の
    0.45
    par
    0.45
     ed
    0.44
     Homem
    0.44
    Activations Density 0.002%

    No Known Activations