© 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. 1-CLT-HP
    7. 13213
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    neurial
    -1.49
    Tikang
    -0.80
    QMetaType
    -0.78
    tagHelperRunner
    -0.75
    sidemargin
    -0.73
    IVEREF
    -0.69
    تقاوى
    -0.66
    KommentareTeilen
    -0.65
     betweenstory
    -0.65
     considérons
    -0.63
    POSITIVE LOGITS
    prepareStatement
    0.58
    ostomy
    0.54
     <<<<<<<<<<<<<<
    0.52
    thodoxy
    0.49
    boutin
    0.48
    hydra
    0.47
     frappe
    0.46
    排
    0.46
    iterranée
    0.46
    nados
    0.45
    Activations Density 0.015%

    No Known Activations