© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91983
    Prev
    Next
    INDEX
    Explanations

    frying, pneumonia, or sentences

    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
    +#+#
    -1.05
     Senses
    -1.00
     Cæsar
    -0.98
     Priory
    -0.97
     row
    -0.94
     Efq
    -0.91
    WebVitals
    -0.91
     fry
    -0.88
     Shakspeare
    -0.85
     Diſ
    -0.82
    POSITIVE LOGITS
     of
    0.71
     and
    0.71
     the
    0.67
     for
    0.66
     that
    0.65
    the
    0.65
    ,
    0.59
     in
    0.57
    .
    0.56
     A
    0.55
    Activations Density 0.122%

    No Known Activations