© 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. 291
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
    em
    -0.54
    apat
    -0.52
     Galloway
    -0.50
    getJSON
    -0.48
    SCA
    -0.47
    jú
    -0.47
    jsii
    -0.47
     Willard
    -0.45
     reg
    -0.45
    ement
    -0.45
    POSITIVE LOGITS
     faſt
    0.80
     pleaſure
    0.74
     houſe
    0.74
     myſelf
    0.73
     whoſe
    0.72
     Monfieur
    0.71
     purpoſe
    0.71
     theſe
    0.70
    +#+#
    0.70
     reaſon
    0.69
    Activations Density 0.027%

    No Known Activations