© 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. 0-CLT-HP
    7. 42533
    Prev
    Next
    INDEX
    Explanations

    locations, organizations, last names

    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
     Burk
    -0.79
     Cuff
    -0.65
    存于互联网档案馆
    -0.58
    OLIC
    -0.56
    WEBPACK
    -0.54
    archiviato
    -0.52
    multicolumn
    -0.52
    abestanden
    -0.50
    Бахар
    -0.50
     مشين
    -0.49
    POSITIVE LOGITS
    Rüyada
    0.71
    IndentedString
    0.60
     laterale
    0.59
    americanos
    0.57
     pernas
    0.56
    s
    0.53
    ']").
    0.53
     armband
    0.52
     diagnosed
    0.52
    ly
    0.51
    Activations Density 0.837%

    No Known Activations