© 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. 20-CLT-HP
    7. 74753
    Prev
    Next
    INDEX
    Explanations

    SA

    np_max-act-logits · 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
    WindowConstants
    -0.66
    __*/
    -0.61
    Spoljašnje
    -0.60
    __":
    -0.58
    >//
    -0.56
    GIH
    -0.56
    prechen
    -0.55
    cipais
    -0.55
    AndroidJUnit
    -0.55
     препратки
    -0.55
    POSITIVE LOGITS
    UpdateTime
    0.46
    ixeira
    0.44
    قایناق‌لار
    0.43
    ynos
    0.42
     militaire
    0.42
    ResourceType
    0.41
     besök
    0.41
    szak
    0.40
     abbandon
    0.40
    みてください
    0.40
    Activations Density 0.002%

    No Known Activations