© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16059
    Prev
    Next
    INDEX
    Explanations

    camb

    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
    Negative Logits
     SwitchCompat
    -0.64
    LayoutConstraint
    -0.63
     getItemId
    -0.62
    ----</
    -0.60
    exitRule
    -0.58
    migrationBuilder
    -0.57
    itemBuilder
    -0.55
    ToMany
    -0.54
    IsMutable
    -0.52
    Filmografie
    -0.50
    POSITIVE LOGITS
     protoimpl
    0.69
     BrowserModule
    0.60
    ########.
    0.60
    ніципа
    0.58
    +};
    0.51
    bewerken
    0.51
     transférez
    0.50
    ">${
    0.50
     שוליים
    0.50
     vian
    0.50
    Activations Density 0.011%

    No Known Activations