© 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. 1-RES-MATRYOSHKA-DC
    7. 693
    Prev
    Next
    INDEX
    Explanations

    references to specific follow-up activities or assessments

    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
     seguinte
    -1.37
     following
    -1.32
     seguente
    -1.12
     siguiente
    -1.09
     följande
    -1.09
     seguintes
    -1.08
     siguientes
    -1.07
    following
    -1.07
     følgende
    -1.05
     folgende
    -1.03
    POSITIVE LOGITS
     follow
    2.53
    Follow
    2.52
     Follow
    2.48
     FOLLOW
    2.33
    follow
    2.30
     followed
    2.08
    followed
    1.93
     follows
    1.84
     Followed
    1.80
    follows
    1.66
    Activations Density 0.049%

    No Known Activations