© 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. 272
    Prev
    Next
    INDEX
    Explanations

    size and limits

    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
    ArrowToggle
    -1.02
     pinulongan
    -0.71
    ConstraintMaker
    -0.70
    TagMode
    -0.69
     lenker
    -0.69
     متعلقه
    -0.67
    StoryboardSegue
    -0.67
    PreferredItem
    -0.66
     totul
    -0.65
     Roskov
    -0.64
    POSITIVE LOGITS
     there
    0.79
     some
    0.71
     most
    0.63
     we
    0.59
     has
    0.56
     the
    0.52
     of
    0.48
     needs
    0.48
     these
    0.47
     often
    0.47
    Activations Density 0.004%

    No Known Activations