© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95302
    Prev
    Next
    INDEX
    Explanations

    inches quotation mark

    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
    "
    -1.16
     "
    -1.12
     
    -1.09
    <eos>
    -0.94
    ↵↵
    -0.92
    ,
    -0.90
    »
    -0.85
    ”
    -0.85
      
    -0.82
    .
    -0.79
    POSITIVE LOGITS
     myſelf
    1.55
     itſelf
    1.41
    ſelves
    1.35
     Efq
    1.34
     Monfieur
    1.34
     purpoſe
    1.31
     ſche
    1.27
     houſe
    1.26
    ſelf
    1.25
     greateſt
    1.24
    Activations Density 0.028%

    No Known Activations