© 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. 95090
    Prev
    Next
    INDEX
    Explanations

    code and reports

    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
     OMITBAD
    -0.71
    setVerticalGroup
    -0.68
     nahilalakip
    -0.64
     kasarigan
    -0.62
    Rujuakan
    -0.62
    󠁢
    -0.60
    elemField
    -0.60
    adpleegd
    -0.59
     насеље
    -0.57
    unhofer
    -0.56
    POSITIVE LOGITS
    Datuak
    0.63
    Aiheesta
    0.59
    enumii
    0.50
     PyQt
    0.50
    lagt
    0.48
    "])
    0.48
    ");
    0.47
     Ginn
    0.46
    ="@+
    0.46
     befind
    0.46
    Activations Density 0.012%

    No Known Activations