© 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. 44227
    Prev
    Next
    INDEX
    Explanations

    pitched

    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
    ICH
    -1.02
    ichi
    -1.02
    windowFixed
    -0.77
     ICH
    -0.73
    s
    -0.72
    pitched
    -0.71
    ContentAsync
    -0.65
    san
    -0.63
     تضيفلها
    -0.63
     umane
    -0.59
    POSITIVE LOGITS
    TagMode
    0.61
    ScopeManager
    0.59
    ized
    0.56
    IBarButtonItem
    0.55
    NgModule
    0.54
    rzost
    0.48
    ement
    0.46
    ERG
    0.46
    AGAN
    0.46
    Segoe
    0.46
    Activations Density 1.716%

    No Known Activations