© 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. 20-CLT-HP
    7. 71749
    Prev
    Next
    INDEX
    Explanations

    non-english words

    np_max-act-logits · 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
    extAlignment
    -0.47
    roleum
    -0.42
     six
    -0.40
     Del
    -0.39
     Biôgrafia
    -0.39
    Behavior
    -0.39
    __*/
    -0.39
     Ld
    -0.39
    таратура
    -0.38
    sou
    -0.37
    POSITIVE LOGITS
     étrangère
    0.64
    saraba
    0.60
    Capítulo
    0.58
    BufferException
    0.57
    bbene
    0.57
     chemise
    0.56
     Gallimard
    0.55
     OnInit
    0.55
     blessés
    0.55
     CURIAM
    0.54
    Activations Density 0.001%

    No Known Activations