© 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. 15822
    Prev
    Next
    INDEX
    Explanations

    millennium

    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
    rrggbb
    -0.62
    tvguidetime
    -0.56
     الرياضيه
    -0.56
     cielos
    -0.56
     alluminio
    -0.56
     ddelweddau
    -0.50
    hoi
    -0.49
    #+#
    -0.49
    المراجع
    -0.49
    úgó
    -0.48
    POSITIVE LOGITS
     pinulongan
    0.59
    a
    0.58
     abel
    0.57
    OGND
    0.57
    ⓧ
    0.54
    expert
    0.53
    ️
    0.52
    TypedDataSet
    0.52
    ngdoc
    0.52
     faro
    0.50
    Activations Density 0.019%

    No Known Activations