© 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. 1683
    Prev
    Next
    INDEX
    Explanations

    KY

    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
    ida
    -0.37
    ques
    -0.36
     l
    -0.36
    LLABLE
    -0.36
    RICT
    -0.36
    nis
    -0.35
    té
    -0.35
     le
    -0.35
    rict
    -0.35
    lec
    -0.34
    POSITIVE LOGITS
    s
    0.98
     myſelf
    0.83
     againſt
    0.77
     raiſ
    0.77
     itſelf
    0.77
     fubject
    0.75
     poffible
    0.73
     ſtill
    0.72
     himſelf
    0.71
     themſelves
    0.71
    Activations Density 0.539%

    No Known Activations