© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45173
    Prev
    Next
    INDEX
    Explanations

    morals and respect

    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
     synap
    -0.82
    tvguidetime
    -0.80
     purpoſe
    -0.78
     greateſt
    -0.76
     Efq
    -0.75
     coö
    -0.75
    VERTISEMENT
    -0.73
     ſche
    -0.73
     Theſe
    -0.73
     ſtate
    -0.72
    POSITIVE LOGITS
    elemField
    0.49
    .
    0.48
     for
    0.47
     lead
    0.45
    cookieParser
    0.45
    FormTagHelper
    0.44
    Personendaten
    0.42
    photobucket
    0.41
    Raise
    0.40
    巻
    0.39
    Activations Density 0.070%

    No Known Activations