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. 74274
    Prev
    Next
    INDEX
    Explanations

    cross

    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
     the
    -0.74
     them
    -0.71
     <<<<<<<<<<<<<<
    -0.67
    jects
    -0.63
    closePath
    -0.62
    ViewFeatures
    -0.62
    RenderAtEndOf
    -0.60
    ownik
    -0.60
    othes
    -0.59
    lings
    -0.59
    POSITIVE LOGITS
    UNRELATED
    0.47
     déclarations
    0.46
    spro
    0.46
    Levi
    0.44
     circonstances
    0.44
    spra
    0.44
    Kesimpulan
    0.42
    tidak
    0.42
     numéros
    0.42
     cumplen
    0.41
    Activations Density 0.003%

    No Known Activations