© 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. 22-RES-MATRYOSHKA-DC
    7. 2686
    Prev
    Next
    INDEX
    Explanations

    the word "animal" in the context of veterinary medicine or animal practices

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.74
    omány
    -0.65
    AndEndTag
    -0.64
    حوالہ
    -0.63
    RenderAtEndOf
    -0.61
    BorderFactory
    -0.60
    Ārējās
    -0.59
    ніципа
    -0.59
    Referències
    -0.58
    undred
    -0.57
    POSITIVE LOGITS
     animals
    1.15
     animal
    1.02
     Animals
    0.94
    animal
    0.90
     ANIMALS
    0.89
     animale
    0.88
     animales
    0.87
    Animals
    0.87
     animali
    0.85
     mammals
    0.84
    Activations Density 0.190%

    No Known Activations