© 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. 95034
    Prev
    Next
    INDEX
    Explanations

    morality and ethics

    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
    MigrationBuilder
    -0.62
     AssemblyCulture
    -0.60
    <bos>
    -0.51
     FetchType
    -0.47
    getDescriptor
    -0.46
    webElementXpaths
    -0.46
    webElement
    -0.44
    hermes
    -0.41
    thodox
    -0.41
    ondi
    -0.41
    POSITIVE LOGITS
    
    0.70
     themſelves
    0.58
    OrWhiteSpace
    0.58
     صوتيه
    0.58
     Harm
    0.58
     myſelf
    0.57
    거나
    0.56
     TAMBÉM
    0.56
     himſelf
    0.56
    tvguidetime
    0.56
    Activations Density 0.011%

    No Known Activations