© 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. 9105
    Prev
    Next
    INDEX
    Explanations

    git

    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
    VersionUID
    -0.54
     שוליים
    -0.52
    سین
    -0.48
    ICZ
    -0.47
    samples
    -0.47
    bing
    -0.47
    SNE
    -0.47
    pian
    -0.47
    !(:
    -0.47
    sApp
    -0.46
    POSITIVE LOGITS
    AsUp
    0.74
    Filmographie
    0.65
     समीक्षक
    0.57
    skjaer
    0.56
     विश्वसनीयता
    0.55
    IVEREF
    0.53
    ulkner
    0.53
     Chwiliwch
    0.52
    ifflin
    0.51
    Географи
    0.50
    Activations Density 0.024%

    No Known Activations