© 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. 0-RES-MATRYOSHKA-DC
    7. 10916
    Prev
    Next
    INDEX
    Explanations

    references to specific roles or functions related to biological processes or proteins

    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
    ">//
    -0.67
     role
    -0.54
    hein
    -0.54
    andExpect
    -0.52
    nonatomic
    -0.50
     caráter
    -0.50
    que
    -0.49
     micros
    -0.48
    showConfirm
    -0.48
    oluene
    -0.48
    POSITIVE LOGITS
     roles
    2.22
     Roles
    1.96
    roles
    1.72
    Roles
    1.61
     rôles
    1.47
    ROLES
    1.15
     papeles
    0.96
     Rollen
    0.93
     rollen
    0.82
    TagMode
    0.71
    Activations Density 0.005%

    No Known Activations