© 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. 96150
    Prev
    Next
    INDEX
    Explanations

    screen issues

    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
    '
    -0.44
     EdgeInsets
    -0.44
     ist
    -0.42
    XCT
    -0.41
    gca
    -0.40
     послу
    -0.40
    gard
    -0.38
     слу
    -0.38
     or
    -0.37
    ことです
    -0.37
    POSITIVE LOGITS
     jsPsych
    0.70
    StructEnd
    0.69
    Хьажоргаш
    0.69
    IGraphics
    0.66
     FILL
    0.62
     SqlParameter
    0.61
     ")");
    0.60
     Walkover
    0.60
    ScopeManager
    0.59
    __*/
    0.59
    Activations Density 0.019%

    No Known Activations