© 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. 38609
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Sucesor
    -0.57
    Koordinaten
    -0.52
    Ārējās
    -0.45
     PublicKey
    -0.45
     now
    -0.43
     coper
    -0.43
    εί
    -0.43
    Bronnen
    -0.43
    Breaker
    -0.42
     αντί
    -0.41
    POSITIVE LOGITS
    ValueStyle
    0.93
    PreferredItem
    0.90
     Administrativna
    0.74
     '\\;'
    0.74
     démocr
    0.73
    |}{$
    0.73
    PerformLayout
    0.71
    writeFieldEnd
    0.70
    GEBURTSDATUM
    0.69
    aarrggbb
    0.68
    Activations Density 0.459%

    No Known Activations