© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93144
    Prev
    Next
    INDEX
    Explanations

    measurement

    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
     egiten
    -0.55
     nämlich
    -0.54
     infatti
    -0.53
     ver
    -0.52
    GTCX
    -0.52
    <bos>
    -0.52
     bowiem
    -0.51
     ujednoznacz
    -0.51
    __':
    -0.50
    etal
    -0.50
    POSITIVE LOGITS
     enfans
    0.66
     greateſt
    0.64
     houſe
    0.63
     ſmall
    0.63
     ſtate
    0.62
     Majefty
    0.62
     étoit
    0.61
     AppColors
    0.59
    contentLoaded
    0.57
     beſt
    0.57
    Activations Density 0.010%

    No Known Activations