© 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. 5-CLT-HP
    7. 91540
    Prev
    Next
    INDEX
    Explanations

    T

    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
     سكانية
    -0.71
    
    -0.63
     بيها
    -0.63
    endwhile
    -0.63
    Datuak
    -0.62
    #+#
    -0.59
    ಈ
    -0.58
    ViewFeatures
    -0.57
     continúas
    -0.56
     getView
    -0.56
    POSITIVE LOGITS
    ContentAsync
    0.60
    NOPQRST
    0.56
    XmlAccessType
    0.52
     levantó
    0.51
    ArgsConstructor
    0.49
     spørsmål
    0.49
     religieuses
    0.48
    angsaan
    0.46
     spørs
    0.44
    SequentialGroup
    0.44
    Activations Density 0.039%

    No Known Activations