© 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. 0-RES-MATRYOSHKA-DC
    7. 15144
    Prev
    Next
    INDEX
    Explanations

    relationships or connections between items

    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
    তথ্যসূত্র
    -0.68
     onCancelled
    -0.59
    Дереккөздер
    -0.58
    حوالہ
    -0.56
    乓
    -0.55
     للمعارف
    -0.54
    Hozzáférés
    -0.53
    था
    -0.52
    日閲覧
    -0.51
     continúas
    -0.50
    POSITIVE LOGITS
     relate
    1.88
    relate
    1.62
     relatable
    0.86
     resonate
    0.75
     empathi
    0.67
     Rel
    0.66
     correlate
    0.66
     relat
    0.66
     sympathize
    0.62
    Rel
    0.62
    Activations Density 0.001%

    No Known Activations