© 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. 3-RES-MATRYOSHKA-DC
    7. 1473
    Prev
    Next
    INDEX
    Explanations

    chemical formulas, components, and phases.

    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
    Дереккөздер
    -0.55
     going
    -0.52
    KommentareTeilen
    -0.52
    Viitteet
    -0.50
    postmedia
    -0.46
    TargetApi
    -0.46
    DeleteBehavior
    -0.46
     Unito
    -0.46
     meg
    -0.45
     zar
    -0.45
    POSITIVE LOGITS
     myſelf
    0.75
     beſt
    0.74
     Monfieur
    0.69
    setVerticalGroup
    0.69
     ſtate
    0.67
     himſelf
    0.65
     ſever
    0.64
     themſelves
    0.63
     beft
    0.63
    ſelf
    0.63
    Activations Density 0.654%

    No Known Activations