© 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. 77602
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation

    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
    äksi
    -0.51
     insecto
    -0.49
    balleur
    -0.48
    <!--[
    -0.47
     Economía
    -0.47
    CreateModel
    -0.47
    ulism
    -0.46
    sedi
    -0.45
    diali
    -0.45
     ahi
    -0.44
    POSITIVE LOGITS
    webElement
    0.76
    intios
    0.68
    PyTuple
    0.65
     Newbury
    0.63
    principalTable
    0.59
    parsedMessage
    0.59
    ➟
    0.59
     الحره
    0.59
    TagMode
    0.58
    ++];
    0.57
    Activations Density 0.000%

    No Known Activations