© 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. 4297
    Prev
    Next
    INDEX
    Explanations

    robust

    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
     Audiodateien
    -0.56
     WebDriverWait
    -0.53
    -------------</
    -0.53
     Phoen
    -0.52
    afone
    -0.52
    flap
    -0.51
    ingtones
    -0.50
    atilde
    -0.50
    สัม
    -0.49
    AsStream
    -0.49
    POSITIVE LOGITS
    قایناق‌لار
    0.71
    tagHelperRunner
    0.60
    Спољашње
    0.58
    GenerationType
    0.56
    conio
    0.51
    انيف
    0.51
    ArgsConstructor
    0.49
    SourceChecksum
    0.49
    Datuak
    0.48
    jooq
    0.47
    Activations Density 0.001%

    No Known Activations