Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12160
    Prev
    Next
    INDEX
    Explanations

    Sci-Fi/technical writing

    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
    <>();
    -0.56
    <bos>
    -0.53
     na
    -0.47
    readFileSync
    -0.44
     “
    -0.44
     Topf
    -0.42
    greenrobot
    -0.42
     John
    -0.42
     δια
    -0.41
     Kemp
    -0.41
    POSITIVE LOGITS
     myſelf
    0.85
     itſelf
    0.82
     Efq
    0.79
     Monfieur
    0.70
     whoſe
    0.68
     becauſe
    0.68
     ſeveral
    0.66
     reaſon
    0.66
     faſt
    0.66
     laſt
    0.65
    Activations Density 0.014%

    No Known Activations