© 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. 2-RES-MATRYOSHKA-DC
    7. 7090
    Prev
    Next
    INDEX
    Explanations

    references to materials containing salt, grease, dirt, and corrosion

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.63
    المناصب
    -0.63
    jface
    -0.60
    biť
    -0.57
     باخ
    -0.57
     Gopal
    -0.56
    
    -0.56
     geda
    -0.55
    */;
    -0.55
     vux
    -0.55
    POSITIVE LOGITS
     salt
    1.34
    salt
    1.24
     Salt
    1.22
    Salt
    1.19
     powder
    1.10
     mud
    1.05
     Powder
    1.03
     dirt
    1.01
    powder
    0.97
    dirt
    0.97
    Activations Density 0.491%

    No Known Activations