© 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. 90497
    Prev
    Next
    INDEX
    Explanations

    code or lists

    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
    li
    -0.91
     li
    -0.84
     v
    -0.77
    n
    -0.58
    asers
    -0.57
    ness
    -0.56
     Li
    -0.51
    esi
    -0.49
    nu
    -0.47
     vi
    -0.47
    POSITIVE LOGITS
     Anſ
    0.88
     Houſe
    0.84
     myſelf
    0.83
     Efq
    0.82
     ſind
    0.81
     purpoſe
    0.80
     greateſt
    0.80
    tvguidetime
    0.79
     houſe
    0.78
     pleaſure
    0.77
    Activations Density 1.680%

    No Known Activations