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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73964
    Prev
    Next
    INDEX
    Explanations

    Mixed content

    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
    katapos
    -0.52
     répondu
    -0.50
    izielle
    -0.49
    essoal
    -0.49
    Diweddarwch
    -0.48
     euer
    -0.48
    aters
    -0.48
     Makers
    -0.48
    springframework
    -0.48
    habitants
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.76
     "..\..\..\
    0.56
     typelib
    0.56
    HideFlags
    0.55
     "..\..\
    0.53
    nologue
    0.52
     lenker
    0.52
    enumi
    0.52
    ########.
    0.50
     الرياضيه
    0.50
    Activations Density 0.000%

    No Known Activations