© 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. 73693
    Prev
    Next
    INDEX
    Explanations

    Stanis

    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
    tagHelperRunner
    -0.98
    SequentialGroup
    -0.86
     AssemblyCulture
    -0.81
    bootstrapcdn
    -0.80
    ^(@)
    -0.72
    NUMX
    -0.71
    niająca
    -0.71
     Paglinawan
    -0.70
    izowane
    -0.69
     Vri
    -0.68
    POSITIVE LOGITS
    rxjs
    0.37
     only
    0.35
     trị
    0.35
    -
    0.35
    er
    0.33
     for
    0.33
    getInputStream
    0.32
     ter
    0.32
     no
    0.32
     from
    0.31
    Activations Density 0.000%

    No Known Activations