© 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. 5-CLT-HP
    7. 5584
    Prev
    Next
    INDEX
    Explanations

    division or separation

    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
    rungsseite
    -0.98
    ConstraintMaker
    -0.87
     Chwiliwch
    -0.84
    Хьажоргаш
    -0.79
    enumi
    -0.78
     AppColors
    -0.78
     snippetHide
    -0.76
    VersionUID
    -0.75
     WaitForSeconds
    -0.74
    Tembelea
    -0.74
    POSITIVE LOGITS
     in
    0.54
     on
    0.51
    .
    0.45
     (
    0.42
     by
    0.40
    ,
    0.40
     -
    0.40
    id
    0.40
    Id
    0.39
    ;
    0.38
    Activations Density 0.001%

    No Known Activations