© 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. 1077
    Prev
    Next
    INDEX
    Explanations

    sentences or statements that assert precise or exact measurements or values

    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
     særlig
    -0.58
     particularmente
    -0.56
    собенно
    -0.56
     considér
    -0.54
     particularly
    -0.53
     especialmente
    -0.53
    ∉
    -0.52
    gogo
    -0.51
     szczególnie
    -0.51
    יקר
    -0.50
    POSITIVE LOGITS
     exactly
    4.22
     exact
    4.06
    exactly
    3.97
     Exactly
    3.80
     Exact
    3.61
    Exactly
    3.58
    exact
    3.56
     precisely
    3.52
     EXACTLY
    3.42
    Exact
    3.33
    Activations Density 0.393%

    No Known Activations