© 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. 5-CLT-HP
    7. 96096
    Prev
    Next
    INDEX
    Explanations

    Undoing/cancelling actions

    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
     defStyleAttr
    -0.48
    ">:
    -0.48
    iecie
    -0.44
    pra
    -0.43
     ویکی‌پدیای
    -0.43
     interviewers
    -0.43
     jdbcTemplate
    -0.42
    faces
    -0.41
    Viki
    -0.40
    UCA
    -0.40
    POSITIVE LOGITS
    ConstraintMaker
    0.75
    RegressionTest
    0.66
    quelize
    0.65
    NameInMap
    0.61
     فريبيس
    0.59
    WithMany
    0.59
    المناصب
    0.58
    Composable
    0.57
     lenker
    0.56
    letzt
    0.56
    Activations Density 0.001%

    No Known Activations