© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1549
    Prev
    Next
    INDEX
    Explanations

    Enumerating features/specifications

    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
     originais
    -0.70
     vieilles
    -0.68
     originaux
    -0.65
    RUnlock
    -0.64
    PerformLayout
    -0.64
     portée
    -0.61
     CURIAM
    -0.60
     riuscito
    -0.59
     afgelopen
    -0.59
     desconhe
    -0.57
    POSITIVE LOGITS
     a
    1.05
     an
    0.71
     the
    0.70
     multiple
    0.57
    hnung
    0.55
     two
    0.48
     parallel
    0.47
     including
    0.46
    jiga
    0.45
     use
    0.45
    Activations Density 0.005%

    No Known Activations