© 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. 4494
    Prev
    Next
    INDEX
    Explanations

    Code and scientific texts

    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
     LIABLE
    -0.57
     Kuri
    -0.54
     ECB
    -0.50
     Shaksp
    -0.49
     Whitby
    -0.48
    AddRef
    -0.48
     Eindruck
    -0.48
    hounds
    -0.48
    cplusplus
    -0.48
     rato
    -0.48
    POSITIVE LOGITS
     Seminar
    0.79
    Seminar
    0.73
    ValueStyle
    0.71
    seminar
    0.64
     ProtoMessage
    0.62
    MarshalTo
    0.62
     Seminars
    0.62
     seminar
    0.61
    richTextPanel
    0.59
     Glove
    0.58
    Activations Density 0.000%

    No Known Activations