© 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. 20-CLT-HP
    7. 71680
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act-logits · 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
    脚注の使い方
    -0.86
     actionMode
    -0.85
    yntaxException
    -0.81
    XmlAccessType
    -0.81
     onAnimation
    -0.80
    ContentAsync
    -0.75
    principalColumn
    -0.75
     ddelweddau
    -0.74
    ::::::::
    -0.68
     ModelExpression
    -0.66
    POSITIVE LOGITS
     within
    0.78
     time
    0.70
     among
    0.68
     atop
    0.63
     beneath
    0.61
     scratch
    0.60
    m
    0.60
     across
    0.58
     under
    0.57
     around
    0.57
    Activations Density 0.300%

    No Known Activations