© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45513
    Prev
    Next
    INDEX
    Explanations

    storey

    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
    httphttps
    -0.96
    évaluateur
    -0.80
     الحره
    -0.80
     regress
    -0.79
    PreferredItem
    -0.77
    Diweddarwch
    -0.76
     cref
    -0.75
     المعيارى
    -0.75
    endphp
    -0.75
     autorytatywna
    -0.74
    POSITIVE LOGITS
    actor
    0.60
     per
    0.51
    ed
    0.47
    as
    0.47
    ne
    0.47
    ir
    0.47
    num
    0.47
    x
    0.46
    ap
    0.46
    af
    0.46
    Activations Density 0.079%

    No Known Activations