© 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. 1-CLT-HP
    4. 13336
    Prev
    Next
    INDEX
    Explanations

    asties

    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
     autorytatywna
    -1.09
    makeText
    -0.73
    IndentedString
    -0.70
    VIAF
    -0.70
    acyjny
    -0.69
     resourceCulture
    -0.68
    principalTable
    -0.67
    ÚBL
    -0.66
    ύ
    -0.64
    /-/
    -0.61
    POSITIVE LOGITS
    MessageOf
    0.54
     []).
    0.49
    적
    0.48
    ReusableCell
    0.48
     Donny
    0.47
    vation
    0.46
     Pind
    0.44
    civ
    0.44
    ally
    0.44
     Sciento
    0.44
    Activations Density 0.021%

    No Known Activations