© 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. 7087
    Prev
    Next
    INDEX
    Explanations

    snippets of code, technical documentation, or references to software licensing and legal information

    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
    raszamy
    -0.59
    URUS
    -0.56
     ơn
    -0.55
    躇
    -0.54
    UserDTO
    -0.54
    omentos
    -0.53
     messen
    -0.53
    zbęd
    -0.52
    scrollY
    -0.52
    NonQuery
    -0.52
    POSITIVE LOGITS
    oredCriteria
    1.84
    MigrationBuilder
    1.76
    تقاوى
    1.74
    GEBURTSDATUM
    1.73
     beginnetje
    1.73
    rungsseite
    1.59
     nahilalakip
    1.58
    Personensuche
    1.50
    adaptiveStyles
    1.48
    AutoScaleMode
    1.45
    Activations Density 4.015%

    No Known Activations