© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94985
    Prev
    Next
    INDEX
    Explanations

    code/legal context

    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
     Medea
    -0.89
     Meksiku
    -0.54
     geboten
    -0.48
    :✨
    -0.47
    tonode
    -0.47
     članak
    -0.46
     Geister
    -0.45
     Meister
    -0.44
    AnimationsModule
    -0.44
    withIdentifier
    -0.44
    POSITIVE LOGITS
     nahilalakip
    0.66
    ￡
    0.59
     Rans
    0.57
    AlterField
    0.57
    reshed
    0.56
    pernicus
    0.55
     nî
    0.54
    urable
    0.53
    ontent
    0.53
    setVerticalGroup
    0.51
    Activations Density 0.001%

    No Known Activations