© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71580
    Prev
    Next
    INDEX
    Explanations

    Mixed content and topics

    np_max-act-logits · 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
    
    -0.68
     Exactos
    -0.59
    GOTREF
    -0.54
    bable
    -0.54
    存于互联网档案馆
    -0.52
     doInBackground
    -0.52
    edel
    -0.52
    ✨:
    -0.51
    zdy
    -0.50
    IndentedString
    -0.50
    POSITIVE LOGITS
     correctes
    0.60
    XmlSchema
    0.60
    الحياه
    0.53
     firebaseConfig
    0.49
    nien
    0.47
    XmlAccessType
    0.47
    kapet
    0.47
    жере
    0.47
     Cop
    0.46
    IZONT
    0.46
    Activations Density 0.000%

    No Known Activations