© 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. 76195
    Prev
    Next
    INDEX
    Explanations

    Varied and technical contexts

    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
    kening
    -0.55
    Presenting
    -0.53
    lanes
    -0.52
     GoogleFonts
    -0.50
    enumii
    -0.49
     presenting
    -0.49
     себе
    -0.48
     nakalista
    -0.47
    yanto
    -0.47
    ?></
    -0.47
    POSITIVE LOGITS
    Brainz
    0.71
     kasarigan
    0.65
    qrstuvwxyz
    0.62
     المعيارى
    0.59
    Спољашње
    0.59
    цездатний
    0.58
    OGND
    0.56
    addContainerGap
    0.55
    aarrggbb
    0.55
     Waw
    0.53
    Activations Density 0.000%

    No Known Activations