© 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. 45791
    Prev
    Next
    INDEX
    Explanations

    electronics and physics

    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
    t
    -0.52
    d
    -0.50
    ty
    -0.49
     ei
    -0.43
    l
    -0.42
    check
    -0.42
    dan
    -0.42
     och
    -0.41
    下的
    -0.41
    يانة
    -0.41
    POSITIVE LOGITS
    ModelAdmin
    0.76
    VIAF
    0.74
    󠁣
    0.70
     ſta
    0.68
     faſt
    0.67
     LUMP
    0.67
    .*")]
    0.66
    ModelSerializer
    0.66
    Portail
    0.66
     ſtate
    0.66
    Activations Density 0.011%

    No Known Activations