© 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. 1-CLT-HP
    7. 15367
    Prev
    Next
    INDEX
    Explanations

    legs

    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
     ']
    -0.46
    <bos>
    -0.45
    \"");
    -0.42
    maal
    -0.42
     ivelany
    -0.41
    ностран
    -0.40
     aDecoder
    -0.39
    Flynn
    -0.38
    sine
    -0.37
    setArguments
    -0.37
    POSITIVE LOGITS
    SizeF
    0.80
    ValueStyle
    0.79
    tagHelperRunner
    0.77
     Normdatei
    0.75
     cherchés
    0.71
    oredCriteria
    0.69
     ddelweddau
    0.68
     validamos
    0.67
    IANGLES
    0.67
     виправивши
    0.66
    Activations Density 0.027%

    No Known Activations