© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93668
    Prev
    Next
    INDEX
    Explanations

    1

    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
    falfa
    -0.53
    ‌ای
    -0.48
    ษัท
    -0.47
    cemia
    -0.46
     hice
    -0.45
     culturelles
    -0.45
     Beers
    -0.45
    mousemove
    -0.44
     Commissione
    -0.44
    ῷ
    -0.44
    POSITIVE LOGITS
    بوابة
    0.68
    ⓧ
    0.68
    دانشنامهٔ
    0.64
     defaultstate
    0.63
    ">—
    0.60
     Réponses
    0.59
     esboço
    0.59
     oprot
    0.56
    jspx
    0.56
    ullable
    0.56
    Activations Density 0.000%

    No Known Activations