© 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. 4550
    Prev
    Next
    INDEX
    Explanations

    instructions

    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
     للمعارف
    -1.02
    IntoConstraints
    -0.71
     cherchés
    -0.69
    unknownFields
    -0.66
     /*#__
    -0.63
     препратки
    -0.63
    __":
    -0.60
     تضيفلها
    -0.59
    delwed
    -0.59
     BoxDecoration
    -0.57
    POSITIVE LOGITS
     your
    0.87
     practically
    0.60
     both
    0.56
    ftagPool
    0.54
     any
    0.52
    your
    0.50
     all
    0.50
    yeur
    0.49
     every
    0.49
     and
    0.49
    Activations Density 0.002%

    No Known Activations