© 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. 5-CLT-HP
    7. 96056
    Prev
    Next
    INDEX
    Explanations

    code or configuration snippets

    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
    <bos>
    -0.50
    :
    -0.47
     themſelves
    -0.47
     myſelf
    -0.47
    ​—
    -0.46
    enumi
    -0.46
    ,
    -0.45
     entanto
    -0.44
     thyself
    -0.44
    Validated
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.79
    DoubleQuotes
    0.73
    ]='\
    0.71
     NSCoder
    0.71
    DockStyle
    0.70
     متعلقه
    0.69
    uxxxx
    0.69
    最快更新
    0.68
     “
    0.67
    Autoritní
    0.66
    Activations Density 0.001%

    No Known Activations