© 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. 42783
    Prev
    Next
    INDEX
    Explanations

    impossible

    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
    possible
    -1.56
     possible
    -1.53
     posibles
    -1.31
     Possible
    -1.30
    Possible
    -1.29
     possível
    -1.28
     possibile
    -1.25
     possíveis
    -1.24
     POSSIBLE
    -1.23
     posible
    -1.22
    POSITIVE LOGITS
    ည်
    0.50
     purific
    0.50
     intra
    0.49
     Milestone
    0.48
     existence
    0.48
     acto
    0.48
     ato
    0.48
     dual
    0.47
    ambo
    0.47
     haz
    0.46
    Activations Density 0.111%

    No Known Activations