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. 0-CLT-HP
    4. 91392
    Prev
    Next
    INDEX
    Explanations

    science

    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
    theless
    -0.97
     ویکی‌پدی
    -0.94
    ſelf
    -0.93
    UnusedPrivate
    -0.92
    StoryboardSegue
    -0.92
    __":
    
    -0.91
    stuffs
    -0.90
    ſelves
    -0.90
    🏼
    -0.83
     Wikimedijinoj
    -0.82
    POSITIVE LOGITS
     and
    0.59
    ,
    0.52
     of
    0.47
     couche
    0.46
    ť
    0.45
     anden
    0.43
    .
    0.42
     to
    0.42
     or
    0.42
     sola
    0.40
    Activations Density 0.090%

    No Known Activations