© 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. 4069
    Prev
    Next
    INDEX
    Explanations

    phrases related to highlighting significant or impactful effects

    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
    InlineData
    -0.70
    asuring
    -0.68
    ANDUM
    -0.67
    delà
    -0.65
    \{\\
    -0.64
    manteau
    -0.63
     Италијани
    -0.63
    lamabad
    -0.63
    mayın
    -0.62
    ubehör
    -0.61
    POSITIVE LOGITS
     possessed
    0.90
     experienced
    0.86
     possess
    0.86
     faced
    0.84
     posed
    0.76
     possesses
    0.75
     Faced
    0.75
    Poss
    0.74
     Poss
    0.73
     incurred
    0.73
    Activations Density 0.645%

    No Known Activations