© 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. 0-CLT-HP
    7. 42245
    Prev
    Next
    INDEX
    Explanations

    piano

    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
    ness
    -0.77
     delivery
    -0.74
     piano
    -0.73
    ly
    -0.67
    ened
    -0.62
    mals
    -0.60
     free
    -0.59
     Delivery
    -0.58
    ste
    -0.54
    free
    -0.53
    POSITIVE LOGITS
    ]")]
    0.71
    +#+#
    0.71
     autorización
    0.66
     المعيارى
    0.63
     termica
    0.62
     mukana
    0.58
     validés
    0.57
    nobyl
    0.57
     passés
    0.56
    väg
    0.56
    Activations Density 0.074%

    No Known Activations