© 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. 538
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     disease
    -0.68
     diagnosis
    -0.57
    onAttach
    -0.56
    disease
    -0.54
     diseases
    -0.53
     patient
    -0.49
     continúas
    -0.48
     health
    -0.47
    Disease
    -0.47
     diagnoses
    -0.47
    POSITIVE LOGITS
     ddelweddau
    0.70
    >`;
    0.64
    migrationBuilder
    0.63
     Paglinawan
    0.60
     Wiktionnaire
    0.60
    ConstraintMaker
    0.58
     Depression
    0.58
    afficheront
    0.56
    findpost
    0.55
     CascadeType
    0.55
    Activations Density 0.010%

    No Known Activations