© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-RES-MATRYOSHKA-DC
    7. 29851
    Prev
    Next
    INDEX
    Explanations

    the word "sister"

    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
    مراجع
    -0.76
    UMENTS
    -0.72
     horaires
    -0.70
    ftagPool
    -0.69
     Gad
    -0.65
    postmedia
    -0.65
    agno
    -0.65
     Mace
    -0.64
    endroit
    -0.63
    avaj
    -0.63
    POSITIVE LOGITS
    Sister
    1.23
     Sister
    1.21
     sisters
    1.17
     Sisters
    1.16
    Sisters
    1.14
     sister
    1.12
    sisters
    1.05
    sister
    1.04
     Brito
    0.93
     sis
    0.88
    Activations Density 0.005%

    No Known Activations