© 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. 0-CLT-HP
    7. 91094
    Prev
    Next
    INDEX
    Explanations

    membership

    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
    tainer
    -0.52
    served
    -0.47
    tained
    -0.46
     as
    -0.42
    tainers
    -0.42
    št
    -0.40
     TEMPLE
    -0.40
     als
    -0.40
     fehl
    -0.39
     feather
    -0.38
    POSITIVE LOGITS
    /**
    0.80
    StoreMessageInfo
    0.80
    SourceChecksum
    0.78
    bootstrapcdn
    0.77
    principalColumn
    0.75
    RTLD
    0.74
     itſelf
    0.74
     Efq
    0.73
     незавершена
    0.73
    OOTDTY
    0.73
    Activations Density 1.341%

    No Known Activations