© 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. 97417
    Prev
    Next
    INDEX
    Explanations

    auto

    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
     ainfi
    -0.91
     plufieurs
    -0.89
     auroit
    -0.86
     étoit
    -0.85
    fjspx
    -0.85
     mourut
    -0.84
    BeginContext
    -0.83
     pouvoit
    -0.83
     auto
    -0.81
     feroit
    -0.80
    POSITIVE LOGITS
    e
    0.59
    i
    0.52
    jsii
    0.49
    gu
    0.48
    h
    0.45
    v
    0.44
    a
    0.42
    im
    0.42
    ch
    0.42
    w
    0.41
    Activations Density 0.046%

    No Known Activations