© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76185
    Prev
    Next
    INDEX
    Explanations

    op

    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
    webElementXpaths
    -0.92
    complexContent
    -0.74
    ]")]
    -0.73
    :✨
    -0.66
     noqa
    -0.65
    AnchorTagHelper
    -0.65
    onOptions
    -0.63
    GIH
    -0.62
    rrggbb
    -0.62
     externi
    -0.62
    POSITIVE LOGITS
    atch
    0.53
    end
    0.49
    harusnya
    0.47
    endis
    0.44
    den
    0.43
    datac
    0.42
    Kag
    0.42
    uten
    0.41
     sè
    0.41
     ed
    0.40
    Activations Density 0.002%

    No Known Activations