© 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. 1-CLT-HP
    7. 15168
    Prev
    Next
    INDEX
    Explanations

    alco

    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
     gouttes
    -0.64
    Personensuche
    -0.62
     InputDecoration
    -0.60
     Romains
    -0.59
    entibus
    -0.58
     nuages
    -0.57
     larmes
    -0.56
    værende
    -0.56
    Šaltiniai
    -0.56
     gelap
    -0.56
    POSITIVE LOGITS
    /*---
    0.54
    llong
    0.53
     creep
    0.52
    WithIOException
    0.51
    StoreMessageInfo
    0.51
    }^{+\
    0.50
    RTEE
    0.50
     yal
    0.49
     Viol
    0.47
     Pati
    0.46
    Activations Density 0.001%

    No Known Activations