© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96608
    Prev
    Next
    INDEX
    Explanations

    compar

    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
     noDo
    -0.92
    GEBURTSDATUM
    -0.85
    abestanden
    -0.84
    OGND
    -0.82
    IndentedString
    -0.79
     utafitiHapana
    -0.78
     typelib
    -0.77
     Wikimedijinoj
    -0.77
    ymce
    -0.73
     kasarigan
    -0.72
    POSITIVE LOGITS
    Circle
    0.45
     dissection
    0.43
    -
    0.40
     domini
    0.40
     circle
    0.39
     patr
    0.39
    v
    0.37
     wst
    0.36
     xuyên
    0.35
     Circle
    0.35
    Activations Density 0.000%

    No Known Activations