© 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. 9803
    Prev
    Next
    INDEX
    Explanations

    ub

    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
    abetes
    -0.60
     beginnetje
    -0.59
    ГЛА
    -0.55
    InitVars
    -0.54
    Extinguishing
    -0.50
     AllAfrica
    -0.47
    Jeografia
    -0.47
     picioare
    -0.47
     quedado
    -0.46
    olone
    -0.46
    POSITIVE LOGITS
     BoxFit
    0.64
     Booth
    0.54
     Rok
    0.54
     Puerta
    0.50
    rido
    0.49
    tur
    0.49
    StringCopy
    0.48
    дения
    0.48
     Marks
    0.48
    ery
    0.47
    Activations Density 0.058%

    No Known Activations