© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119353
    Prev
    Next
    INDEX
    Explanations

    aggregation and pooling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    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
     cliquant
    -0.06
     clicar
    -0.06
     relevant
    -0.06
     etc
    -0.06
     apparaître
    -0.06
     despertar
    -0.06
     cliquer
    -0.06
     Clicking
    -0.06
    のと
    -0.05
     rust
    -0.05
    POSITIVE LOGITS
    传感
    0.06
     ming
    0.06
     osoby
    0.06
     moitié
    0.06
    楹
    0.06
     विशिष्ट
    0.05
    mixing
    0.05
    SENSOR
    0.05
     Diaries
    0.05
     типи
    0.05
    Activations Density 0.005%

    No Known Activations