© 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. 0-RES-MATRYOSHKA-DC
    7. 12177
    Prev
    Next
    INDEX
    Explanations

    references to the concept of ropes or similar flexible lifting or tying devices

    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
     <=",
    -0.74
    govina
    -0.65
     ddelweddau
    -0.60
     صوتيه
    -0.60
    точник
    -0.60
    躇
    -0.60
    scut
    -0.59
    setVerticalGroup
    -0.57
    tvr
    -0.57
    Portale
    -0.57
    POSITIVE LOGITS
     rope
    3.48
     ropes
    3.17
    rope
    3.17
     Rope
    2.97
    Rope
    2.56
    ロープ
    1.27
     cuerda
    1.10
     corda
    1.09
    绳
    0.99
    繩
    0.89
    Activations Density 0.019%

    No Known Activations