© 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. 93383
    Prev
    Next
    INDEX
    Explanations

    time or frequency

    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
     while
    -1.44
    while
    -1.27
     along
    -1.16
     once
    -1.05
     mientras
    -0.94
    ,
    -0.93
     and
    -0.90
     mentre
    -0.89
    once
    -0.88
     While
    -0.86
    POSITIVE LOGITS
     Efq
    1.53
     myſelf
    1.45
     purpoſe
    1.45
     itſelf
    1.40
     ſeveral
    1.38
     faſt
    1.38
     houſe
    1.36
     uſe
    1.34
     Monfieur
    1.34
     ſmall
    1.33
    Activations Density 0.083%

    No Known Activations