© 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. 45405
    Prev
    Next
    INDEX
    Explanations

    critters

    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
     Ha
    -0.91
    ha
    -0.81
     ha
    -0.81
    l
    -0.73
    Ha
    -0.70
     N
    -0.67
     
    -0.67
     F
    -0.63
      
    -0.62
     on
    -0.62
    POSITIVE LOGITS
     Reſ
    1.38
    ſelf
    1.32
     purpoſe
    1.32
    ſelves
    1.30
     ſtate
    1.26
     myſelf
    1.26
     houſe
    1.25
     pleaſure
    1.25
     ſche
    1.23
     Efq
    1.23
    Activations Density 0.420%

    No Known Activations