© 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. 1-CLT-HP
    7. 927
    Prev
    Next
    INDEX
    Explanations

    the

    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
    MENAFN
    -0.69
    skraft
    -0.59
    GraphicsUnit
    -0.59
     or
    -0.57
     BoxFit
    -0.57
    intenant
    -0.57
    balleur
    -0.56
    სქოლიო
    -0.55
    Manbalar
    -0.55
     Архів
    -0.54
    POSITIVE LOGITS
    rrggbb
    0.53
    uracy
    0.48
    GNUC
    0.47
     препратки
    0.47
    EditorBrowsable
    0.46
    <?
    0.44
    ControllerAdvice
    0.43
     correctes
    0.43
    Rüyada
    0.42
     whoever
    0.42
    Activations Density 0.014%

    No Known Activations