© 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. 5-CLT-HP
    7. 96231
    Prev
    Next
    INDEX
    Explanations

    Technical/Code Documents

    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
    šech
    -0.48
     importants
    -0.47
     geplant
    -0.47
    RenderAtEndOf
    -0.47
     întâ
    -0.46
    NewGuid
    -0.46
    DockStyle
    -0.45
     colorés
    -0.45
     nimic
    -0.44
     juges
    -0.44
    POSITIVE LOGITS
     someone
    0.75
    Personensuche
    0.70
    OGND
    0.66
     Someone
    0.63
     يتيمه
    0.62
    someone
    0.61
    WebVitals
    0.60
    Someone
    0.60
    expandindo
    0.59
    exitRule
    0.58
    Activations Density 0.003%

    No Known Activations