© 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. 0-CLT-HP
    7. 45436
    Prev
    Next
    INDEX
    Explanations

    degrees and comparisons

    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
     relative
    -1.71
    relative
    -1.71
     total
    -1.62
    Relative
    -1.48
     Relative
    -1.44
    total
    -1.43
    absolute
    -1.43
     absolute
    -1.42
    Total
    -1.38
     totale
    -1.34
    POSITIVE LOGITS
    y
    0.61
    ton
    0.58
     Normdatei
    0.57
    tie
    0.54
     civilian
    0.54
    tling
    0.54
    ties
    0.53
    tly
    0.52
    ty
    0.52
    lification
    0.52
    Activations Density 0.056%

    No Known Activations