© 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. 1-CLT-HP
    7. 401
    Prev
    Next
    INDEX
    Explanations

    days

    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
     avoient
    -0.74
     Meksiku
    -0.73
    OrBuilder
    -0.72
    apimachinery
    -0.69
    ValueStyle
    -0.68
     auroit
    -0.66
    parsedMessage
    -0.64
     pouvoit
    -0.64
    prefixer
    -0.63
     feroit
    -0.63
    POSITIVE LOGITS
     Gregory
    0.49
     Charles
    0.47
     Edward
    0.47
     William
    0.46
    ington
    0.45
     Edmund
    0.43
    rom
    0.41
    Gregory
    0.41
     Dame
    0.41
     Sir
    0.40
    Activations Density 0.046%

    No Known Activations