© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91053
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    ci
    -0.57
     new
    -0.51
     (
    -0.45
    '
    -0.44
    vc
    -0.44
    new
    -0.43
    6
    -0.43
     “
    -0.43
     abge
    -0.41
     x
    -0.41
    POSITIVE LOGITS
    Datuak
    0.93
    RRect
    0.90
     Infórmanos
    0.88
     Anſ
    0.86
    ^(@)
    0.83
     cherchés
    0.82
    Rujuakan
    0.81
     JpaRepository
    0.80
     DOWNVOTE
    0.80
    rawDesc
    0.79
    Activations Density 0.816%

    No Known Activations