Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30889
    Prev
    Next
    INDEX
    Explanations

    words related to soft, supportive objects

    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
    erweise
    -0.83
    zeitige
    -0.78
     Herak
    -0.74
    igneur
    -0.73
    hassee
    -0.73
    ICLES
    -0.71
     Neves
    -0.71
     Peralta
    -0.70
    delaire
    -0.68
     Yah
    -0.68
    POSITIVE LOGITS
     Pillow
    1.63
     pillow
    1.61
     pillows
    1.61
    Pillow
    1.50
    pillow
    1.43
     cushion
    1.20
     cushions
    1.18
     Cushion
    1.12
     PILL
    1.06
     coussin
    0.99
    Activations Density 0.002%

    No Known Activations