© 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. 4-CLT-HP
    7. 4556
    Prev
    Next
    INDEX
    Explanations

    legal/software references

    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
    ciaż
    -0.58
    حياته
    -0.52
    modb
    -0.50
     Вікі
    -0.50
    ariats
    -0.50
    UrlResolution
    -0.50
    ritch
    -0.49
     TextInputType
    -0.48
    tonode
    -0.48
     يتيمه
    -0.48
    POSITIVE LOGITS
     виправивши
    0.68
     onCreateView
    0.61
    Bibliograf
    0.59
    ########.
    0.56
     autorytatywna
    0.54
    횟
    0.53
     internetowa
    0.52
     maschile
    0.52
    Искәрмәләр
    0.50
     hermanos
    0.49
    Activations Density 0.011%

    No Known Activations