© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42056
    Prev
    Next
    INDEX
    Explanations

    who

    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
     épaules
    -0.52
    žná
    -0.47
     ervan
    -0.46
     rzecz
    -0.45
     églises
    -0.45
     heißt
    -0.44
     δὲ
    -0.44
     vroe
    -0.44
     normes
    -0.44
     llaves
    -0.43
    POSITIVE LOGITS
     @"/
    0.94
    <bos>
    0.93
    AndEndTag
    0.90
    AnchorStyles
    0.82
     NSCoder
    0.82
    StoryboardSegue
    0.81
     <=",
    0.77
    PerformLayout
    0.76
    Билгалдахарш
    0.76
    withIdentifier
    0.75
    Activations Density 0.054%

    No Known Activations