© 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. 45110
    Prev
    Next
    INDEX
    Explanations

    Purposes

    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
     myſelf
    -1.59
     Efq
    -1.48
     itſelf
    -1.48
     purpoſe
    -1.46
     pleaſure
    -1.43
    ſelf
    -1.40
     themſelves
    -1.36
     Jefus
    -1.34
    neſs
    -1.34
     raiſ
    -1.31
    POSITIVE LOGITS
    <eos>
    0.75
    a
    0.69
     consectetur
    0.62
     Her
    0.61
     
    0.59
    ’
    0.59
    on
    0.59
    en
    0.57
    ↵↵
    0.56
    '
    0.56
    Activations Density 0.059%

    No Known Activations