© 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. 6-RES-MATRYOSHKA-DC
    7. 616
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the importance or role of something

    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
     Grafton
    -0.55
     formData
    -0.54
     conditions
    -0.53
     brut
    -0.52
    Garcia
    -0.52
    monia
    -0.52
    tı
    -0.52
     Kitz
    -0.52
     Etwas
    -0.51
     Hauts
    -0.51
    POSITIVE LOGITS
     role
    2.38
     roles
    2.14
     Role
    2.14
     ROLE
    2.13
     Roles
    2.05
    Role
    1.95
    role
    1.93
     rôle
    1.92
    ROLE
    1.90
     ruolo
    1.80
    Activations Density 1.086%

    No Known Activations