© 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. 3-RES-MATRYOSHKA-DC
    7. 1879
    Prev
    Next
    INDEX
    Explanations

    the words "after" and "before"

    oai_token-act-pair · gemini-2.0-flash
    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
     follow
    -1.29
    follows
    -1.27
    follow
    -1.21
     follows
    -1.18
     FOLLOW
    -1.13
    FOLLOW
    -1.09
     Follows
    -1.08
     следу
    -1.07
    Follow
    -1.02
     Follow
    -1.01
    POSITIVE LOGITS
    After
    2.27
     after
    2.23
     After
    2.22
    after
    2.19
     AFTER
    1.92
    AFTER
    1.84
     dopo
    1.69
     après
    1.55
     Après
    1.52
     Dopo
    1.50
    Activations Density 0.258%

    No Known Activations