© 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. 1-CLT-HP
    7. 10765
    Prev
    Next
    INDEX
    Explanations

    field

    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
    PLANATION
    -0.60
     godk
    -0.60
    umą
    -0.57
     الرياضيه
    -0.57
     MediaQuery
    -0.56
     betale
    -0.56
    XmlAccessType
    -0.55
    TargetApi
    -0.54
    TemporalType
    -0.53
     bicchiere
    -0.53
    POSITIVE LOGITS
     Clé
    0.52
    
    0.52
     Vira
    0.51
    (")");
    0.47
     succession
    0.47
     cerevisiae
    0.46
    InputTagHelper
    0.46
    posedge
    0.45
     accuracy
    0.44
     plankton
    0.44
    Activations Density 0.018%

    No Known Activations