© 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. 93849
    Prev
    Next
    INDEX
    Explanations

    new

    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
     initComponents
    -0.79
    WithIOException
    -0.77
    parsedMessage
    -0.76
    GEBURTSDATUM
    -0.73
     виправивши
    -0.72
     disambiguazione
    -0.70
     defaultstate
    -0.68
    complexContent
    -0.67
    ChildIndex
    -0.67
    IsMutable
    -0.66
    POSITIVE LOGITS
     Turks
    0.51
    ferrous
    0.50
     kapag
    0.44
    findpost
    0.44
     chrétien
    0.40
     metallurgical
    0.40
     teď
    0.40
    OLOGY
    0.40
     biais
    0.40
     tere
    0.40
    Activations Density 0.002%

    No Known Activations