© 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. 2954
    Prev
    Next
    INDEX
    Explanations

    references to the number four or related numerical references

    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
    ThroughAttribute
    -1.02
    StoryboardSegue
    -0.77
    :✨
    -0.73
    verwijspagina
    -0.70
    esgue
    -0.68
     pamphlets
    -0.66
    DataAnnotations
    -0.64
    LLocation
    -0.64
     Assignee
    -0.64
     tabPage
    -0.64
    POSITIVE LOGITS
     heres
    0.69
    Voici
    0.68
    Heres
    0.67
     here
    0.65
     voici
    0.64
     Voici
    0.59
    Lets
    0.59
     Lets
    0.57
     Here
    0.54
     şöyle
    0.53
    Activations Density 0.059%

    No Known Activations