© 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. 2-RES-MATRYOSHKA-DC
    7. 5077
    Prev
    Next
    INDEX
    Explanations

    references to points of high significance, particularly the word "point" with a high activation value

    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
     points
    -0.76
    Points
    -0.70
     Points
    -0.69
    points
    -0.59
     POINTS
    -0.59
    POINTS
    -0.49
     punten
    -0.49
     `
    -0.48
    <eos>
    -0.48
     '
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    0.84
    tvguidetime
    0.82
    WebVitals
    0.80
     doubtnut
    0.80
     myſelf
    0.75
     للاسماء
    0.73
    migrationBuilder
    0.72
    glise
    0.70
    elebr
    0.69
    קישורים
    0.69
    Activations Density 0.021%

    No Known Activations