© 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. 3-RES-MATRYOSHKA-DC
    7. 1652
    Prev
    Next
    INDEX
    Explanations

    the word "family" and related words

    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
    iono
    -0.56
    OrNil
    -0.55
     Quell
    -0.54
     JpaRepository
    -0.53
     mother
    -0.53
     Dice
    -0.53
    protoimpl
    -0.53
     Grind
    -0.53
     Ure
    -0.53
    anke
    -0.52
    POSITIVE LOGITS
     team
    2.22
     Team
    2.08
    Team
    2.05
    team
    2.05
     staff
    2.02
     family
    1.99
    TEAM
    1.97
    family
    1.95
     TEAM
    1.91
     Staff
    1.91
    Activations Density 0.471%

    No Known Activations