© 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. 0-CLT-HP
    7. 92187
    Prev
    Next
    INDEX
    Explanations

    degrees, hip

    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
    -1.14
    <bos>
    -1.09
     auffi
    -1.05
     Efq
    -1.00
     myſelf
    -0.94
    DockStyle
    -0.94
    __":
    -0.93
     themſelves
    -0.91
     ―――――
    -0.89
     ſhe
    -0.88
    POSITIVE LOGITS
    .
    0.54
    :
    0.52
    !
    0.48
    io
    0.44
    <strong>
    0.42
    (
    0.42
    ?
    0.42
    …
    0.41
    <b>
    0.40
    ic
    0.40
    Activations Density 0.218%

    No Known Activations