© 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. 20-CLT-HP
    7. 73334
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · 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
     after
    -1.00
     AFTER
    -0.83
    after
    -0.79
     después
    -0.78
     afterwards
    -0.77
     afterward
    -0.77
     dopo
    -0.75
     após
    -0.75
     після
    -0.75
     après
    -0.74
    POSITIVE LOGITS
     the
    1.17
    šní
    0.49
    the
    0.43
    grano
    0.43
    \"");
    0.42
    fmf
    0.41
     GenerationType
    0.41
    photobucket
    0.41
    toMap
    0.40
    mayr
    0.40
    Activations Density 0.000%

    No Known Activations