© 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. 4-CLT-HP
    7. 392
    Prev
    Next
    INDEX
    Explanations

    phy

    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
    PreferredItem
    -0.66
     propOrder
    -0.64
     שוליים
    -0.60
    userdetails
    -0.60
     الرياضيه
    -0.59
     ITIS
    -0.58
     كومونز
    -0.58
     وتسجيلات
    -0.57
    apati
    -0.57
    __":
    -0.57
    POSITIVE LOGITS
     versa
    0.50
    SSA
    0.46
    hima
    0.45
    алу
    0.44
     متعلقه
    0.42
    anna
    0.41
    proken
    0.41
    cuta
    0.41
    ANNA
    0.40
    quium
    0.40
    Activations Density 0.001%

    No Known Activations