© 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. 1-CLT-HP
    7. 15175
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · 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
    tadır
    -0.57
    expandindo
    -0.56
    揄
    -0.56
     affatto
    -0.55
     trataba
    -0.55
    devamını
    -0.53
     sentimenti
    -0.52
     compleanno
    -0.52
     attualmente
    -0.52
     utilizzando
    -0.51
    POSITIVE LOGITS
    DoubleQuotes
    0.69
    kháu
    0.52
    Define
    0.51
     pageable
    0.50
    <bos>
    0.49
     define
    0.49
    </thead>
    0.49
    lexikon
    0.49
     SEP
    0.49
    umerate
    0.47
    Activations Density 0.012%

    No Known Activations