© 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. 0-RES-MATRYOSHKA-DC
    7. 11313
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "match" or similar expressions related to matching or matching criteria

    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
    matches
    -1.02
    matching
    -0.99
     matching
    -0.90
    matched
    -0.89
     Matching
    -0.89
    matcher
    -0.85
    .*")]
    -0.82
     Matches
    -0.80
    Matching
    -0.75
     matches
    -0.73
    POSITIVE LOGITS
     match
    0.69
     ευ
    0.66
     fit
    0.61
    好
    0.60
    حوالہ
    0.59
    Mens
    0.56
    illiard
    0.54
    trell
    0.54
     صوتيه
    0.53
    ghold
    0.52
    Activations Density 0.009%

    No Known Activations