© 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. 14404
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
     contextLoads
    -0.73
    OGND
    -0.69
    ftagPool
    -0.66
    Personendaten
    -0.64
    存于互联网档案馆
    -0.64
     médicaux
    -0.63
     strerror
    -0.63
     JpaRepository
    -0.61
     feroit
    -0.61
     TabLayout
    -0.60
    POSITIVE LOGITS
     on
    0.60
     into
    0.57
     of
    0.56
    poca
    0.55
     On
    0.55
     amp
    0.53
    津
    0.51
    Życiorys
    0.50
    <bos>
    0.49
     in
    0.49
    Activations Density 0.019%

    No Known Activations