© 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. 14627
    Prev
    Next
    INDEX
    Explanations

    organized

    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
     Audiodateien
    -0.66
    corrhi
    -0.56
    URLException
    -0.56
     officiellement
    -0.55
     للاسماء
    -0.54
     obé
    -0.54
     gills
    -0.52
    ecio
    -0.52
     distanciation
    -0.51
    HostException
    -0.51
    POSITIVE LOGITS
     plan
    0.59
     fashion
    0.57
     manner
    0.56
    ностран
    0.54
     itinéraires
    0.51
     look
    0.50
     way
    0.50
    ссмо
    0.50
     Normdatei
    0.49
     approach
    0.49
    Activations Density 0.004%

    No Known Activations