© 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. 6169
    Prev
    Next
    INDEX
    Explanations

    vocabulary associated with immune responses and viral 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
    __':
    -0.72
    Autoritní
    -0.68
     BnF
    -0.64
    calientes
    -0.61
     appelez
    -0.60
    providedIn
    -0.59
     AttributeSet
    -0.59
     ExecuteAsync
    -0.56
     SIMBAD
    -0.56
    __':
    -0.56
    POSITIVE LOGITS
     oamen
    0.60
     laterales
    0.54
     åren
    0.52
     amarillas
    0.52
    itás
    0.51
    Begriffsklä
    0.50
     tuturor
    0.50
     militaires
    0.47
    RetentionPolicy
    0.47
    ThroughAttribute
    0.46
    Activations Density 1.630%

    No Known Activations