© 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. 97032
    Prev
    Next
    INDEX
    Explanations

    approximations

    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
     helst
    -0.48
     européennes
    -0.48
    Referencias
    -0.45
    новниш
    -0.42
    Which
    -0.42
    发表于
    -0.41
     preocupes
    -0.41
     Архів
    -0.41
    もちろん
    -0.41
     noires
    -0.41
    POSITIVE LOGITS
    featureID
    0.84
     the
    0.73
     when
    0.70
     our
    0.66
     disambiguazione
    0.62
    GEBURTSDATUM
    0.60
     marking
    0.59
    ⓧ
    0.59
     cytok
    0.59
     how
    0.59
    Activations Density 0.001%

    No Known Activations