© 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. 287
    Prev
    Next
    INDEX
    Explanations

    references to speech or statements made by individuals

    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
    mobileqq
    -0.59
     Staub
    -0.54
     αποτε
    -0.53
     toán
    -0.52
    pett
    -0.51
    InkWell
    -0.49
    ymce
    -0.49
     lesson
    -0.49
    jle
    -0.49
    muk
    -0.48
    POSITIVE LOGITS
     said
    4.03
    said
    3.53
    Said
    3.31
     says
    3.27
     Said
    3.16
     say
    3.09
     SAID
    3.08
    says
    2.95
     Says
    2.92
    Says
    2.89
    Activations Density 0.548%

    No Known Activations