© 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. 2-RES-MATRYOSHKA-DC
    7. 4015
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "follows" or "following" in a 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
    uride
    -0.69
     subsequent
    -0.68
     following
    -0.67
    DataAnnotations
    -0.66
    lıyor
    -0.65
    endregion
    -0.60
     aspi
    -0.60
    شهاد
    -0.60
     FOLLOWING
    -0.60
     luego
    -0.59
    POSITIVE LOGITS
     follows
    1.25
    follows
    1.11
     FOLLOW
    0.76
     følger
    0.76
     Follows
    0.73
     follow
    0.72
     folgt
    0.72
    Follow
    0.70
     volgt
    0.68
     Follow
    0.67
    Activations Density 0.019%

    No Known Activations