© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1327
    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
    存于互联网档案馆
    -0.71
    Hochspringen
    -0.70
     ostavi
    -0.70
    ArgsConstructor
    -0.68
    SequentialGroup
    -0.67
     مرئيه
    -0.66
     الحره
    -0.63
     незавершена
    -0.60
     NSCoder
    -0.60
    onAttach
    -0.60
    POSITIVE LOGITS
     November
    0.74
     July
    0.73
     December
    0.73
     October
    0.72
     January
    0.72
     September
    0.71
     March
    0.70
     June
    0.69
     February
    0.68
     August
    0.66
    Activations Density 0.053%

    No Known Activations