© 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. 97013
    Prev
    Next
    INDEX
    Explanations

    per

    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
     per
    -1.09
     
    -1.08
     Per
    -1.00
    <bos>
    -0.96
     in
    -0.93
     and
    -0.89
    ↵↵
    -0.88
    ,
    -0.88
    Per
    -0.87
     that
    -0.86
    POSITIVE LOGITS
     Efq
    1.44
     myſelf
    1.41
     Theſe
    1.41
     iſt
    1.27
     purpoſe
    1.27
     Anſ
    1.25
     ſever
    1.25
     Reſ
    1.24
     itſelf
    1.24
     pleaſure
    1.23
    Activations Density 0.124%

    No Known Activations