© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13555
    Prev
    Next
    INDEX
    Explanations

    words related to dedication or commitment, specifically forms of the word "saving."

    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
     Roskov
    -0.75
    __':
    -0.71
     ves
    -0.65
     insuffisamment
    -0.63
    __':
    -0.62
     Ves
    -0.62
    ves
    -0.61
    __":
    -0.60
     JpaRepository
    -0.59
    AutoScaleMode
    -0.58
    POSITIVE LOGITS
    ving
    3.08
    VING
    1.62
    vings
    1.34
    VIAF
    0.79
    vinger
    0.79
    ved
    0.77
     ving
    0.63
    AVING
    0.60
     VIAF
    0.59
     pièce
    0.50
    Activations Density 0.001%

    No Known Activations