© 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. 10509
    Prev
    Next
    INDEX
    Explanations

    muscles

    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
     energetically
    -0.63
     Berto
    -0.58
     Tất
    -0.56
    itename
    -0.56
     Blon
    -0.55
    anwal
    -0.55
    例句
    -0.54
    ulauan
    -0.54
     kepad
    -0.53
     Participate
    -0.53
    POSITIVE LOGITS
    adpleegd
    0.72
    oa̍t
    0.62
     propOrder
    0.60
     kaarangay
    0.57
     jLabel
    0.56
    <bos>
    0.55
    ыгана
    0.52
     cherchés
    0.48
    textTheme
    0.48
     Meksiku
    0.48
    Activations Density 0.075%

    No Known Activations