© 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. 4-CLT-HP
    7. 159
    Prev
    Next
    INDEX
    Explanations

    time

    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
    assium
    -0.51
     jadx
    -0.47
    //
    -0.47
    teady
    -0.47
    agonal
    -0.46
    prefixer
    -0.45
     fault
    -0.45
     PSS
    -0.44
    ctical
    -0.44
     band
    -0.44
    POSITIVE LOGITS
     détru
    0.63
     Tonight
    0.59
     fermés
    0.57
     كومونز
    0.57
     miliki
    0.56
     rapat
    0.56
     pungkasnya
    0.56
    tagHelperRunner
    0.55
     Today
    0.54
    قایناق‌لار
    0.54
    Activations Density 0.045%

    No Known Activations