© 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. 5856
    Prev
    Next
    INDEX
    Explanations

    references to specific wolves and wolf-like characters

    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
     للاسماء
    -0.83
    stdc
    -0.75
    Portale
    -0.70
     CreateTagHelper
    -0.70
    oa̍t
    -0.70
    OGND
    -0.68
    aliana
    -0.66
    ędzy
    -0.64
    mybatisplus
    -0.63
    ondissement
    -0.63
    POSITIVE LOGITS
     Wolf
    1.37
    Wolf
    1.35
     WOLF
    1.26
     wolf
    1.22
     Bear
    1.16
    wolf
    1.16
     Eagle
    1.16
    Bear
    1.12
     Lion
    1.12
     bear
    1.05
    Activations Density 0.467%

    No Known Activations