© 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. 1104
    Prev
    Next
    INDEX
    Explanations

    Non-English and Code

    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
    inga
    -1.43
     oaks
    -1.08
    ing
    -0.69
    ingar
    -0.67
    ingan
    -0.61
    ING
    -0.60
    lioz
    -0.60
    ingos
    -0.60
    IPT
    -0.60
    ings
    -0.59
    POSITIVE LOGITS
    ectady
    0.58
    extAlignment
    0.56
     Ned
    0.49
    esModule
    0.49
     dụ
    0.48
    sticks
    0.47
     Bug
    0.46
    makeConstraints
    0.45
    waves
    0.44
    NUMX
    0.44
    Activations Density 0.106%

    No Known Activations