© 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. 1093
    Prev
    Next
    INDEX
    Explanations

    encyclopedia entries

    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
    клопе
    -0.68
    StoryboardSegue
    -0.68
     ſtate
    -0.66
    uclear
    -0.66
    出版年
    -0.64
     himſelf
    -0.63
     pleaſure
    -0.63
    setVerticalGroup
    -0.63
    esModule
    -0.62
     Pebble
    -0.62
    POSITIVE LOGITS
     mercancías
    0.49
     bäst
    0.47
     jouets
    0.42
     dalamnya
    0.41
     rémun
    0.41
     hemsida
    0.40
     svårt
    0.40
     distribuzione
    0.40
     températures
    0.39
     längre
    0.39
    Activations Density 0.027%

    No Known Activations