© 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. 4-CLT-HP
    7. 1503
    Prev
    Next
    INDEX
    Explanations

    equity

    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
     nakalista
    -0.85
    Portale
    -0.80
    ://$
    -0.77
     שוליים
    -0.76
     وتسجيلات
    -0.76
    ("")]
    -0.75
     noDo
    -0.74
     nonUne
    -0.73
    Diwedd
    -0.70
     Paglinawan
    -0.69
    POSITIVE LOGITS
     tuturor
    0.40
     asemenea
    0.40
    ValueStyle
    0.35
    haya
    0.33
     betreft
    0.33
    смотрим
    0.33
     jeste
    0.33
     deceased
    0.32
    を行います
    0.32
    各项
    0.31
    Activations Density 0.001%

    No Known Activations