© 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. 4-CLT-HP
    7. 233
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    Portail
    -0.68
     незавершена
    -0.65
     للمعارف
    -0.57
     stället
    -0.55
     تانيه
    -0.55
     ?>>
    -0.55
    AndEndTag
    -0.54
    ⓧ
    -0.54
     waaronder
    -0.54
    protoc
    -0.54
    POSITIVE LOGITS
     early
    0.63
    ,
    0.59
     pre
    0.55
     in
    0.54
     earlier
    0.53
     many
    0.53
     unknownFields
    0.52
     long
    0.49
    till
    0.48
     
    0.48
    Activations Density 0.003%

    No Known Activations