© 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. 94810
    Prev
    Next
    INDEX
    Explanations

    launcher, moderator

    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
    Observations
    -0.71
    skraft
    -0.62
     Commentary
    -0.61
     Observations
    -0.60
     fortune
    -0.57
    Commentary
    -0.56
     Ramsey
    -0.51
    Diagnosis
    -0.50
     AssemblyVersion
    -0.49
    ArgumentParser
    -0.48
    POSITIVE LOGITS
    Personensuche
    0.64
     disponibilités
    0.59
     ویکی‌آمباردا
    0.57
     Nearest
    0.56
     nawr
    0.56
    hoea
    0.56
     WQS
    0.56
     utafitiHapana
    0.55
     nearest
    0.54
    󠁢
    0.54
    Activations Density 0.091%

    No Known Activations