© 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. 97277
    Prev
    Next
    INDEX
    Explanations

    twisted

    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
    TintMode
    -0.60
    uri
    -0.59
     issues
    -0.59
    ratio
    -0.52
    share
    -0.49
     cite
    -0.47
     ISSUES
    -0.46
    iseta
    -0.45
    suit
    -0.44
    
    -0.43
    POSITIVE LOGITS
     Theſe
    1.13
     Monfieur
    1.00
     myſelf
    1.00
     houſe
    0.94
     Efq
    0.94
     Houſe
    0.93
     itſelf
    0.91
     Jefus
    0.91
    ſelf
    0.90
     theſe
    0.89
    Activations Density 1.418%

    No Known Activations