© 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. 44113
    Prev
    Next
    INDEX
    Explanations

    enem

    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
    ed
    -0.62
     المعيارى
    -0.59
     autorytatywna
    -0.57
    aure
    -0.57
    UnsafeEnabled
    -0.56
    a
    -0.53
    effect
    -0.51
    entary
    -0.51
    e
    -0.51
    WithIOException
    -0.50
    POSITIVE LOGITS
    psies
    0.60
    ='';
    0.58
    )».
    0.57
     Baillargeon
    0.54
    rophoresis
    0.53
    )++;
    0.53
    ness
    0.52
    ()?;
    0.52
    ()");
    0.51
    épisode
    0.51
    Activations Density 1.350%

    No Known Activations