© 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. 20-CLT-HP
    7. 72654
    Prev
    Next
    INDEX
    Explanations

    net

    np_max-act-logits · 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
     kys
    -0.66
    numerusform
    -0.64
    apimachinery
    -0.60
    findpost
    -0.59
     Intervention
    -0.56
     springfox
    -0.56
     Interventions
    -0.56
     Ils
    -0.56
    gemeinde
    -0.55
     Ideas
    -0.55
    POSITIVE LOGITS
     propOrder
    0.71
    ayaquil
    0.54
    󠁮
    0.51
    wnież
    0.50
    endphp
    0.50
     wireType
    0.50
    ِّف
    0.49
     net
    0.46
    щадь
    0.46
     للاسماء
    0.44
    Activations Density 0.000%

    No Known Activations