© 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. 1233
    Prev
    Next
    INDEX
    Explanations

    wrights

    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
    wrights
    -0.63
    keleton
    -0.62
    keepers
    -0.59
     banding
    -0.57
     EconPapers
    -0.54
    SCOP
    -0.49
    thâu
    -0.48
    contri
    -0.47
     priest
    -0.47
     bishop
    -0.46
    POSITIVE LOGITS
    GraphicsUnit
    0.73
    posedge
    0.66
    EndProject
    0.56
    GeneratedValue
    0.55
     виправивши
    0.55
    اریخ
    0.55
    Abitanti
    0.54
    Демографія
    0.53
    son
    0.52
    DOCTYPE
    0.51
    Activations Density 0.096%

    No Known Activations