© 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. 94543
    Prev
    Next
    INDEX
    Explanations

    assault

    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
     assault
    -0.62
    ondo
    -0.61
    n
    -0.60
    ubel
    -0.54
    orin
    -0.52
    asti
    -0.52
    kosi
    -0.51
    u
    -0.51
    ppo
    -0.49
    borg
    -0.49
    POSITIVE LOGITS
     itſelf
    1.23
     Efq
    1.20
     themſelves
    1.12
     myſelf
    1.10
    InputBorder
    1.09
     ſeveral
    1.09
     Anſ
    1.07
     ་་
    1.07
     purpoſe
    1.07
     ―――――
    1.06
    Activations Density 1.559%

    No Known Activations