© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72846
    Prev
    Next
    INDEX
    Explanations

    a

    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
    __':
    -0.61
    Writes
    -0.57
     nakalista
    -0.57
    Statics
    -0.56
     podjela
    -0.56
    __":
    -0.55
    punten
    -0.55
    WriteAttribute
    -0.54
    InjectAttribute
    -0.54
    <bos>
    -0.53
    POSITIVE LOGITS
     page
    0.62
    Page
    0.55
    page
    0.55
     BoxDecoration
    0.52
    tableFuture
    0.52
     estimés
    0.51
     joy
    0.49
     Page
    0.48
    dett
    0.48
     cherchés
    0.46
    Activations Density 0.002%

    No Known Activations