© 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. 4-CLT-HP
    7. 65
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    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
     can
    -0.66
     did
    -0.60
     have
    -0.60
    NewUrlParser
    -0.56
     has
    -0.56
     will
    -0.55
     had
    -0.54
     uses
    -0.54
     country
    -0.53
     tried
    -0.53
    POSITIVE LOGITS
    دانشنامهٔ
    0.60
    horabuena
    0.58
     Réponses
    0.58
     riduzione
    0.49
     idag
    0.49
     braço
    0.49
    jeux
    0.48
     piedi
    0.47
     Propel
    0.47
     vermelhas
    0.46
    Activations Density 0.001%

    No Known Activations