© 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. 130233
    Prev
    Next
    INDEX
    Explanations

    hydrophobic

    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
     forcing
    -0.06
     збіль
    -0.06
     lawful
    -0.06
    펭
    -0.06
     তথ
    -0.06
    憬
    -0.06
     Jacobian
    -0.06
     Acura
    -0.06
    odils
    -0.06
     laboratorio
    -0.06
    POSITIVE LOGITS
     hydrophobic
    0.08
     dry
    0.07
     kering
    0.07
    Dry
    0.06
     privados
    0.06
    旱
    0.06
     privés
    0.06
     основании
    0.06
     कैश
    0.06
    itted
    0.06
    Activations Density 0.043%

    No Known Activations