© 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. 1-RES-MATRYOSHKA-DC
    7. 307
    Prev
    Next
    INDEX
    Explanations

    variables related to a specific constant or parameter, particularly the variable 'k'

    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
     itſelf
    -0.96
    ſelf
    -0.85
     Jefus
    -0.84
     uſed
    -0.82
     Chriſt
    -0.82
     myſelf
    -0.79
     ſy
    -0.78
     ſtre
    -0.77
     Diſ
    -0.77
     unſ
    -0.75
    POSITIVE LOGITS
    k
    3.28
     k
    3.19
     K
    2.66
    K
    2.55
    к
    1.61
    Ｋ
    1.56
    ｋ
    1.56
    𝑘
    1.52
     К
    1.45
    К
    1.40
    Activations Density 1.905%

    No Known Activations