© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 72073
    Prev
    Next
    INDEX
    Explanations

    Diverse informational sources

    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
    endphp
    -0.61
     aastal
    -0.59
    kids
    -0.54
     Pupil
    -0.54
    Kids
    -0.53
    children
    -0.51
     overla
    -0.51
    </tfoot>
    -0.51
    kään
    -0.51
    hese
    -0.50
    POSITIVE LOGITS
     незавершена
    0.64
    ⓘ
    0.63
    fortawesome
    0.58
    GeneratedCode
    0.56
    aphone
    0.56
    ViewFeatures
    0.55
     saites
    0.53
    naphthal
    0.52
     MacGregor
    0.52
    ThroughAttribute
    0.52
    Activations Density 0.000%

    No Known Activations