© 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. 40565
    Prev
    Next
    INDEX
    Explanations

    ok

    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
    ok
    -1.25
    ala
    -0.85
    OK
    -0.79
     ok
    -0.76
     Ok
    -0.73
    okay
    -0.71
    okk
    -0.70
    yes
    -0.69
     la
    -0.69
    okkal
    -0.67
    POSITIVE LOGITS
     itſelf
    0.79
     Reſ
    0.66
    tamol
    0.64
     Anſ
    0.63
    knapp
    0.60
     wot
    0.60
     Mahomet
    0.60
     stratum
    0.59
     appreci
    0.58
     APL
    0.58
    Activations Density 0.273%

    No Known Activations