© 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. 22-RES-MATRYOSHKA-DC
    7. 1460
    Prev
    Next
    INDEX
    Explanations

    instances of limited knowledge with personal pronouns

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.56
    Itoa
    -0.56
    chez
    -0.51
    erialize
    -0.50
     vPvB
    -0.49
    queryInterface
    -0.49
    bcryptjs
    -0.49
    templateUrl
    -0.48
    mergeFrom
    -0.48
    oneofs
    -0.48
    POSITIVE LOGITS
     know
    3.30
    know
    2.98
     knows
    2.97
    Know
    2.89
     Know
    2.80
     knowing
    2.75
     knew
    2.72
     KNOW
    2.56
     knowledge
    2.55
     Knowing
    2.55
    Activations Density 1.366%

    No Known Activations