Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44438
    Prev
    Next
    INDEX
    Explanations

    item delivery

    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
     InputDecoration
    -1.16
    Geplaatst
    -1.09
     Roskov
    -1.04
    RenderAtEndOf
    -1.03
    setVerticalGroup
    -1.01
     pleaſure
    -1.01
     ModelExpression
    -1.00
     itſelf
    -1.00
     مرئيه
    -0.99
     myſelf
    -0.99
    POSITIVE LOGITS
    }
    0.48
    。
    0.47
    |
    0.47
    )
    0.47
    ,
    0.47
    &
    0.46
    帽
    0.46
    ↵
    0.46
     bū
    0.46
    (
    0.46
    Activations Density 0.425%

    No Known Activations