© 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. 3845
    Prev
    Next
    INDEX
    Explanations

    references to muscle tissue or muscles

    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
    Datuak
    -0.83
    uxxxx
    -0.69
    BeginContext
    -0.69
     समीक्षाओं
    -0.67
     ovi
    -0.61
     Maw
    -0.60
    netbeans
    -0.60
    </tfoot>
    -0.57
     cráneo
    -0.57
     Nucleus
    -0.57
    POSITIVE LOGITS
     muscle
    3.23
     Muscle
    2.89
    muscle
    2.81
    Muscle
    2.70
     muscles
    2.47
     Muscles
    2.14
     muscular
    2.13
     Muskel
    1.96
    肌肉
    1.85
     Muscular
    1.74
    Activations Density 0.010%

    No Known Activations