© 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. 42620
    Prev
    Next
    INDEX
    Explanations

    inescence

    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
     music
    -0.64
     @"/
    -0.57
    ativement
    -0.50
    Diweddarwch
    -0.49
    herited
    -0.48
    windowFixed
    -0.46
    놀
    -0.46
    ències
    -0.45
    defn
    -0.45
     band
    -0.45
    POSITIVE LOGITS
     fevere
    0.76
     فريبيس
    0.72
     alpina
    0.71
     blisters
    0.68
    AutoField
    0.67
     ſever
    0.67
     quæ
    0.67
    +#+#
    0.66
     Cæsar
    0.66
    
    0.65
    Activations Density 0.081%

    No Known Activations