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. 44548
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
    ,
    -0.55
     on
    -0.52
    :
    -0.44
    .
    -0.43
    ing
    -0.43
     in
    -0.43
     that
    -0.43
     by
    -0.43
    ly
    -0.41
     after
    -0.41
    POSITIVE LOGITS
     Theſe
    1.12
     Efq
    1.11
     Anſ
    1.06
     estekak
    1.00
     المعيارى
    1.00
     Monfieur
    1.00
     Jefus
    0.98
    zzleHttp
    0.98
    ^(@)
    0.97
    AutoresizingMask
    0.97
    Activations Density 0.781%

    No Known Activations