© 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. 3929
    Prev
    Next
    INDEX
    Explanations

    references to the feet of individuals, often symbolizing standing, presence, or a metaphor for foundation or purity

    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
     walks
    -0.82
     Walks
    -0.76
    клопе
    -0.71
    TemporalType
    -0.71
     chas
    -0.68
    walks
    -0.66
    +#+
    -0.66
     pinulongan
    -0.65
     Villar
    -0.65
     FOOT
    -0.64
    POSITIVE LOGITS
     feet
    2.38
     Feet
    2.00
    feet
    1.98
     FEET
    1.78
    Feet
    1.56
     Füße
    0.98
     pieds
    0.98
     voeten
    0.91
     pés
    0.83
     Füßen
    0.79
    Activations Density 0.003%

    No Known Activations