© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 507
    Prev
    Next
    INDEX
    Explanations

    years with the number 9 in them

    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
    3
    -0.69
    be
    -0.66
    2
    -0.66
    ள்
    -0.65
    di
    -0.64
     propri
    -0.62
     поло
    -0.62
     vle
    -0.61
     Тол
    -0.60
    一个
    -0.59
    POSITIVE LOGITS
    9
    1.81
     Ninth
    1.72
     NINE
    1.68
     ninety
    1.67
     nine
    1.66
     ninth
    1.63
    nine
    1.57
    ninth
    1.55
     Nine
    1.55
     nueve
    1.49
    Activations Density 3.429%

    No Known Activations