© 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. 4-CLT-HP
    7. 2049
    Prev
    Next
    INDEX
    Explanations

    is

    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
     Reverso
    -0.74
    Personensuche
    -0.69
     Photocase
    -0.69
     typelib
    -0.68
    adpleegd
    -0.67
     OFDb
    -0.67
     Drapeau
    -0.67
     дописавши
    -0.67
    RegressionTest
    -0.66
     ostavi
    -0.65
    POSITIVE LOGITS
     where
    0.67
     were
    0.48
     super
    0.48
    where
    0.46
    writeFieldEnd
    0.45
    super
    0.43
     it
    0.43
    keits
    0.41
    ,
    0.41
     me
    0.40
    Activations Density 0.010%

    No Known Activations