© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1349
    Prev
    Next
    INDEX
    Explanations

    the word "following" and words near it

    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
     after
    -0.80
     After
    -0.78
    After
    -0.78
    after
    -0.74
    AFTER
    -0.64
    Dopo
    -0.60
    Setelah
    -0.59
    Efter
    -0.59
     אחרי
    -0.57
     после
    -0.57
    POSITIVE LOGITS
     following
    1.71
     seguinte
    1.56
     siguiente
    1.42
    following
    1.42
     följande
    1.39
     seguintes
    1.36
     suivante
    1.32
     siguientes
    1.29
     suivantes
    1.28
     folgende
    1.26
    Activations Density 0.120%

    No Known Activations