© 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. 40590
    Prev
    Next
    INDEX
    Explanations

    sacrificing

    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
     sacrificing
    -0.88
     يتيمه
    -0.79
    Geplaatst
    -0.77
    httphttps
    -0.77
    最快更新
    -0.75
     ***!
    -0.73
    bootstrapcdn
    -0.71
     Normdatei
    -0.71
     FetchType
    -0.67
    construct
    -0.67
    POSITIVE LOGITS
     the
    0.56
     an
    0.56
     हुए
    0.52
     familiar
    0.50
    ingly
    0.49
    anea
    0.49
    inya
    0.47
    ability
    0.47
    [++
    0.47
    ész
    0.46
    Activations Density 0.084%

    No Known Activations