© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    technical and organizational terms

    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
     tölt
    -0.51
     fill
    -0.51
     filling
    -0.46
     Fill
    -0.45
     C
    -0.45
    ull
    -0.44
     filled
    -0.43
     par
    -0.42
    Fill
    -0.41
     V
    -0.40
    POSITIVE LOGITS
    uxxxx
    0.94
    GEBURTSDATUM
    0.78
    帖最后由
    0.77
    AnchorStyles
    0.76
    ErrUnexpectedEOF
    0.73
     intptr
    0.72
     invokingState
    0.71
    featureID
    0.71
    новниш
    0.71
    SharedDtor
    0.68
    Activations Density 0.003%

    No Known Activations