© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130444
    Prev
    Next
    INDEX
    Explanations

    1ANT_B_A2DP BIT6

    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
     همچنین
    -0.07
     또한
    -0.07
     также
    -0.06
     ასევე
    -0.06
    :""
    -0.06
     EFFECT
    -0.06
     इत्यादी
    -0.06
     эффект
    -0.05
     STRAIGHT
    -0.05
    1
    -0.05
    POSITIVE LOGITS
     are
    0.08
     risc
    0.06
     Wang
    0.06
     گرفتار
    0.06
     shave
    0.06
     encourages
    0.06
     galera
    0.06
     enfoque
    0.06
     gelen
    0.06
     dith
    0.06
    Activations Density 0.001%

    No Known Activations