© 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. 1-CLT-HP
    7. 15934
    Prev
    Next
    INDEX
    Explanations

    primers

    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
    BIÉN
    -0.54
     educativas
    -0.52
     educativos
    -0.50
    setupUi
    -0.50
     équilibr
    -0.48
    ratie
    -0.47
     gawas
    -0.47
     CWE
    -0.47
    PreExecute
    -0.46
     compréhen
    -0.46
    POSITIVE LOGITS
    enumi
    0.70
     ProtoMessage
    0.58
     صوتيه
    0.56
    rrggbb
    0.53
    tagHelperRunner
    0.53
    募
    0.52
     Falkland
    0.50
     nahilalakip
    0.50
     Lac
    0.50
     recruited
    0.49
    Activations Density 0.020%

    No Known Activations