© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45108
    Prev
    Next
    INDEX
    Explanations

    Bacillus

    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
     invokingState
    -0.76
    rungsseite
    -0.75
    ArrowToggle
    -0.75
    appé
    -0.68
    ToAction
    -0.68
     EClass
    -0.68
     ChromeDriver
    -0.66
     lccn
    -0.66
    ToMany
    -0.65
    ViewImports
    -0.65
    POSITIVE LOGITS
    er
    1.02
    ed
    0.95
    ing
    0.93
    en
    0.92
    es
    0.86
    o
    0.73
    an
    0.73
    est
    0.68
    al
    0.67
    ة
    0.64
    Activations Density 0.095%

    No Known Activations