© 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. 494
    Prev
    Next
    INDEX
    Explanations

    statements asserting or questioning whether something is true or valid

    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
     Majefty
    -1.40
     Jefus
    -1.38
     itſelf
    -1.38
     pleaſure
    -1.36
    ſelf
    -1.30
     purpoſe
    -1.30
     themſelves
    -1.25
     Theſe
    -1.23
     houſe
    -1.23
     Efq
    -1.21
    POSITIVE LOGITS
     am
    0.85
     the
    0.84
     I
    0.69
     not
    0.68
     a
    0.67
     
    0.65
     (
    0.64
     "
    0.62
     in
    0.59
     C
    0.59
    Activations Density 4.042%

    No Known Activations