© 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. 74582
    Prev
    Next
    INDEX
    Explanations

    Code/Licensing

    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
     насељу
    -0.73
    Diwedd
    -0.71
    ########.
    -0.63
    Спасылкі
    -0.59
    Portale
    -0.58
    はじめに
    -0.58
    Życiorys
    -0.56
    RenderAtEndOf
    -0.55
    ListItemIcon
    -0.55
    AndroidJUnit
    -0.55
    POSITIVE LOGITS
    orice
    0.52
    GOOD
    0.48
    seamnă
    0.47
    onViewCreated
    0.47
    arschijnlijk
    0.46
    ்க்க
    0.44
     SwitchCompat
    0.44
    good
    0.43
    ässe
    0.43
     Good
    0.43
    Activations Density 0.001%

    No Known Activations