© 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. 38544
    Prev
    Next
    INDEX
    Explanations

    Raman/Names

    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
     itſelf
    -1.22
     myſelf
    -1.22
     Efq
    -1.16
     avoient
    -1.11
    ſelves
    -1.08
     étoient
    -1.08
     Diſ
    -1.08
     themſelves
    -1.07
     houſe
    -1.05
     feroit
    -1.05
    POSITIVE LOGITS
     
    0.82
      
    0.61
     b
    0.60
    '
    0.60
     I
    0.59
    <eos>
    0.59
     In
    0.59
     est
    0.59
    est
    0.58
     w
    0.58
    Activations Density 0.034%

    No Known Activations