© 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. 1-CLT-HP
    7. 15123
    Prev
    Next
    INDEX
    Explanations

    software validation

    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
     Pilgrims
    -1.25
     Pilgrim
    -0.75
     pilgrims
    -0.70
     pilgrim
    -0.56
    варь
    -0.47
     אותה
    -0.46
    PathParam
    -0.46
     אותו
    -0.45
    WriteAttribute
    -0.45
    ]")]
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.65
    RegistryLite
    0.63
    windowFixed
    0.62
     unknownFields
    0.61
    Jeografia
    0.60
    omás
    0.59
     ivelany
    0.59
    naeus
    0.56
     AspNetCore
    0.56
     squee
    0.55
    Activations Density 0.012%

    No Known Activations