© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42642
    Prev
    Next
    INDEX
    Explanations

    ten

    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
     ten
    -0.58
    tvguidetime
    -0.58
    iotensin
    -0.55
    ÍO
    -0.49
    UNIDENTIFIED
    -0.49
    chränk
    -0.48
    mantec
    -0.47
    psum
    -0.47
    uket
    -0.47
    modium
    -0.46
    POSITIVE LOGITS
     Majefty
    0.85
     perfons
    0.76
     itſelf
    0.74
     themſelves
    0.71
     fubject
    0.69
    Билгалдахарш
    0.67
    *+
    0.65
    ///</
    0.64
     perſon
    0.63
     himſelf
    0.63
    Activations Density 2.350%

    No Known Activations