© 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. 1746
    Prev
    Next
    INDEX
    Explanations

    independence

    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
    UnknownFieldSet
    -0.85
     scales
    -0.81
     MainAxisSize
    -0.80
    Independence
    -0.79
    scales
    -0.79
    GraphicsUnit
    -0.77
    TargetException
    -0.77
     Scales
    -0.75
    Попис
    -0.75
    InjectAttribute
    -0.74
    POSITIVE LOGITS
    glBegin
    0.52
    ofman
    0.49
    طق
    0.47
    новништво
    0.44
    ждую
    0.42
     melainkan
    0.42
    holdet
    0.42
     lengan
    0.41
    CAPTION
    0.40
     zich
    0.40
    Activations Density 1.617%

    No Known Activations