© 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. 94871
    Prev
    Next
    INDEX
    Explanations

    top

    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
     top
    -0.85
     prochaines
    -0.64
    DockStyle
    -0.63
     oreilles
    -0.63
     ouvriers
    -0.59
     négociations
    -0.58
     oídos
    -0.58
    StoreMessageInfo
    -0.57
     prisonniers
    -0.56
    ++]=
    -0.56
    POSITIVE LOGITS
     of
    0.59
     analogues
    0.54
     voices
    0.51
     donors
    0.50
     analogs
    0.50
    ginfo
    0.49
    internalType
    0.48
     agencies
    0.47
     symbols
    0.47
     waivers
    0.47
    Activations Density 0.013%

    No Known Activations