© 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. 390
    Prev
    Next
    INDEX
    Explanations

    instances of the word "like" in text

    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
    ktop
    -0.53
    த
    -0.53
     Farmington
    -0.50
    cision
    -0.50
    تفصیلات
    -0.49
    경
    -0.49
    ════
    -0.48
     StatelessWidget
    -0.48
    libft
    -0.48
    toni
    -0.47
    POSITIVE LOGITS
     like
    4.25
    Like
    3.67
     Like
    3.67
    like
    3.64
     LIKE
    3.53
    LIKE
    3.19
     seperti
    2.47
     likes
    2.23
     Seperti
    2.16
     như
    2.13
    Activations Density 0.248%

    No Known Activations