© 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. 20-CLT-HP
    7. 75508
    Prev
    Next
    INDEX
    Explanations

    Code and text data

    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
    similar
    -0.60
    Similar
    -0.56
     Ähnliche
    -0.55
     FIXED
    -0.54
     Similar
    -0.54
    TagHelper
    -0.52
     RELATIVE
    -0.52
     semej
    -0.52
     Composed
    -0.51
     nakalista
    -0.51
    POSITIVE LOGITS
     a
    0.62
     critical
    0.60
    énez
    0.56
    BeginContext
    0.56
    /*
    0.52
    CopyWith
    0.49
     critically
    0.49
    ΗΣ
    0.49
     needed
    0.47
    mapTo
    0.47
    Activations Density 0.000%

    No Known Activations