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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74579
    Prev
    Next
    INDEX
    Explanations

    Technical context

    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
    Carriera
    -0.66
    orari
    -0.64
     HasFactory
    -0.61
    ogical
    -0.60
    клопе
    -0.60
     fidu
    -0.59
     Zenith
    -0.59
     Италијани
    -0.59
    omeness
    -0.58
     soumettre
    -0.58
    POSITIVE LOGITS
    #+#
    0.54
    ValueStyle
    0.52
    +#+#
    0.49
    ViewImports
    0.48
     ding
    0.47
    DispatchToProps
    0.45
    AndEndTag
    0.44
    mapStateToProps
    0.43
    Xna
    0.42
    PerformLayout
    0.42
    Activations Density 0.003%

    No Known Activations