© 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. 6-RES-MATRYOSHKA-DC
    7. 1160
    Prev
    Next
    INDEX
    Explanations

    the verb "follow"

    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
     Pemberton
    -0.77
     Yag
    -0.69
     McCarty
    -0.69
     Urqu
    -0.69
     Jacobsen
    -0.64
     Bezirk
    -0.63
     Briggs
    -0.62
    рг
    -0.62
     Metzger
    -0.62
     Specimens
    -0.61
    POSITIVE LOGITS
    follow
    1.87
     follow
    1.85
     Follows
    1.80
     follows
    1.77
    Follow
    1.75
     FOLLOW
    1.75
     Follow
    1.71
    follows
    1.71
    Followed
    1.54
    FOLLOW
    1.53
    Activations Density 0.505%

    No Known Activations