© 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. 1-CLT-HP
    7. 9830
    Prev
    Next
    INDEX
    Explanations

    lavi

    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
    STP
    -0.60
     STP
    -0.57
    n
    -0.54
     wipers
    -0.52
    rout
    -0.47
     laine
    -0.47
    rato
    -0.45
    lavi
    -0.45
    mited
    -0.44
    ROWS
    -0.44
    POSITIVE LOGITS
    balleur
    0.76
     تضيفلها
    0.67
    .*")]
    0.59
    choly
    0.56
    verwijspagina
    0.56
    postsleuth
    0.56
    contentLoaded
    0.55
     ***/
    0.54
    writeFieldEnd
    0.53
    bewerken
    0.52
    Activations Density 0.013%

    No Known Activations