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. 74184
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    vaadin
    -0.62
    bitan
    -0.59
    SBATCH
    -0.58
     Severn
    -0.54
     parms
    -0.54
     fathoms
    -0.52
    HtmlAttribute
    -0.52
    roidered
    -0.52
     Loretta
    -0.50
     embroidered
    -0.50
    POSITIVE LOGITS
    TypedDataSet
    0.69
    ThroughAttribute
    0.63
    MigrationBuilder
    0.57
    CodeAttribute
    0.53
     Gon
    0.50
     تانيه
    0.46
    Gon
    0.45
    <?
    0.45
    fil
    0.45
     pinulongan
    0.45
    Activations Density 0.002%

    No Known Activations