© 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. 5-CLT-HP
    7. 4264
    Prev
    Next
    INDEX
    Explanations

    age

    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
     arşivlendi
    -0.54
    ArgsConstructor
    -0.45
     час
    -0.44
    GPL
    -0.44
    bri
    -0.43
     outs
    -0.42
    rungsseite
    -0.42
    Hearts
    -0.40
    rste
    -0.40
    TaskId
    -0.40
    POSITIVE LOGITS
     يتيمه
    0.70
     boy
    0.68
    balleur
    0.65
    PMailer
    0.63
     girl
    0.63
    queryInterface
    0.62
    Espèce
    0.62
     Chihuahua
    0.61
     Wikimedijinoj
    0.60
     Roskov
    0.60
    Activations Density 0.007%

    No Known Activations