© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38247
    Prev
    Next
    INDEX
    Explanations

    Extracted article sections

    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
    ArrowToggle
    -0.72
     disambiguazione
    -0.72
     للاسماء
    -0.71
    AutoScaleMode
    -0.69
     ModelExpression
    -0.66
    VideoCapture
    -0.64
    UnusedPrivate
    -0.62
     وتسجيلات
    -0.61
    Autoritní
    -0.60
    HomeAsUpEnabled
    -0.60
    POSITIVE LOGITS
     the
    0.51
    .”
    0.47
    {{
    0.45
    }];
    0.44
     Heraus
    0.42
    [
    0.41
    ————
    0.40
    dą
    0.40
    bla
    0.40
    
    0.40
    Activations Density 0.030%

    No Known Activations