© 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. 4405
    Prev
    Next
    INDEX
    Explanations

    psychology

    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
    gini
    -0.63
    קישורים
    -0.55
    νή
    -0.54
    notag
    -0.54
    WIRE
    -0.54
    oneer
    -0.53
     merve
    -0.52
    uper
    -0.50
     roues
    -0.50
    visor
    -0.50
    POSITIVE LOGITS
     character
    0.71
     characteristics
    0.69
    tonsoft
    0.63
     traits
    0.60
    BeginContext
    0.57
    CHARACTER
    0.57
     characteristic
    0.56
     CHARACTER
    0.56
     Charakter
    0.55
     conflicts
    0.54
    Activations Density 0.000%

    No Known Activations