© 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. 4-CLT-HP
    7. 4445
    Prev
    Next
    INDEX
    Explanations

    time units

    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
    )";
    -0.68
     BrowserModule
    -0.66
    ()");
    -0.61
    ;">
    -0.60
    GetAsync
    -0.60
    intios
    -0.59
    "):
    -0.57
    laughs
    -0.56
    ():
    -0.54
    )";
    -0.52
    POSITIVE LOGITS
     passed
    0.76
     ago
    0.73
     were
    0.67
     elapsed
    0.66
     after
    0.65
     went
    0.65
     Drapeau
    0.64
    CppMethod
    0.63
     occurred
    0.62
     seemed
    0.61
    Activations Density 0.005%

    No Known Activations