© 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. 4-CLT-HP
    4. 4753
    Prev
    Next
    INDEX
    Explanations

    Tran

    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
     Seeder
    -0.68
     يتيمه
    -0.67
     ainfi
    -0.65
    \{\\
    -0.64
     auffi
    -0.61
    protoimpl
    -0.60
     NUKAT
    -0.59
     raiſ
    -0.58
    ynchronously
    -0.58
    principalColumn
    -0.58
    POSITIVE LOGITS
     –
    0.78
     —
    0.73
     -
    0.71
     ~
    0.67
     ‘
    0.62
     This
    0.60
     ―
    0.59
     “
    0.59
     I
    0.56
     --
    0.56
    Activations Density 0.002%

    No Known Activations