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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45011
    Prev
    Next
    INDEX
    Explanations

    New or unskilled

    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
     itſelf
    -2.14
     myſelf
    -2.09
     Efq
    -2.05
     Monfieur
    -2.00
     Jefus
    -1.96
     ſeveral
    -1.91
     doubtnut
    -1.90
     photolibrary
    -1.89
     ་་
    -1.88
     Theſe
    -1.88
    POSITIVE LOGITS
     of
    1.09
     in
    1.08
     (
    1.08
     
    1.08
    <eos>
    1.00
    ↵
    0.96
     the
    0.95
     I
    0.94
    .
    0.93
     to
    0.92
    Activations Density 0.041%

    No Known Activations