© 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. 1224
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    tagHelperRunner
    -0.75
    SourceChecksum
    -0.61
    ГЛА
    -0.60
    rowy
    -0.53
    []]
    -0.49
    IndentedString
    -0.48
     lapses
    -0.48
    principalTable
    -0.47
     sits
    -0.47
    }")]
    -0.47
    POSITIVE LOGITS
    iastes
    0.66
    kwds
    0.54
    msgSender
    0.53
     argc
    0.51
    VersionUID
    0.51
    ComponentModel
    0.50
    WriteBarrier
    0.49
     useEffect
    0.47
     onBackPressed
    0.46
    otrophic
    0.46
    Activations Density 0.004%

    No Known Activations