© 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. 43113
    Prev
    Next
    INDEX
    Explanations

    discontin

    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
    TagMode
    -0.71
     Bryson
    -0.66
     nakalista
    -0.63
    VersionUID
    -0.63
     Signalez
    -0.63
     Wise
    -0.60
    AccessFile
    -0.60
     typelib
    -0.59
    s
    -0.59
     moo
    -0.57
    POSITIVE LOGITS
     doute
    0.54
    Erreferentziak
    0.50
    oked
    0.49
     noten
    0.49
     cesse
    0.48
    ?,?,
    0.48
     leçon
    0.48
    ścio
    0.48
     médicale
    0.47
    CompleteListener
    0.47
    Activations Density 1.296%

    No Known Activations