© 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. 20-CLT-HP
    7. 77441
    Prev
    Next
    INDEX
    Explanations

    right

    np_max-act-logits · 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
     متعلقه
    -0.88
     Normdatei
    -0.69
    UnitTesting
    -0.63
    CustomAttributes
    -0.61
    createCanvas
    -0.61
     surla
    -0.60
    IndentedString
    -0.60
    󠁴
    -0.59
     محفوظة
    -0.59
    RegistryLite
    -0.59
    POSITIVE LOGITS
     right
    0.93
     quite
    0.75
     great
    0.69
    quite
    0.53
     Right
    0.53
     very
    0.52
     Quite
    0.49
    %)$
    0.47
     RIGHT
    0.45
    Right
    0.45
    Activations Density 0.001%

    No Known Activations