© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92734
    Prev
    Next
    INDEX
    Explanations

    violence/bodily actions

    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
    BeginInit
    -0.56
     urbaine
    -0.56
     humaines
    -0.55
    Atoi
    -0.50
    WhereInput
    -0.50
     SDLK
    -0.49
    Дереккөздер
    -0.49
    adaptiveStyles
    -0.47
     sintética
    -0.47
     marinho
    -0.47
    POSITIVE LOGITS
    <bos>
    0.63
     the
    0.61
    حياته
    0.60
    Statistiche
    0.57
     يتيمه
    0.57
     referenties
    0.55
    addPreferredGap
    0.55
    urally
    0.54
     Clip
    0.54
    malade
    0.54
    Activations Density 0.243%

    No Known Activations