© 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. 29901
    Prev
    Next
    INDEX
    Explanations

    the phrase "form of"

    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
     ſtand
    -0.81
     raiſ
    -0.74
     uſed
    -0.71
     Inga
    -0.70
    rippa
    -0.68
     Wikimedijinoj
    -0.67
     whoſe
    -0.67
     Belgi
    -0.66
     faſt
    -0.66
     ſy
    -0.64
    POSITIVE LOGITS
     !!}
    0.58
    ManyToOne
    0.58
    "],
    0.57
    DIPSETTING
    0.56
     насеље
    0.55
    @[+][
    0.54
    AddTagHelper
    0.54
     GenerationType
    0.54
     SafeMath
    0.53
    )"),
    0.53
    Activations Density 0.021%

    No Known Activations