© 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. 29921
    Prev
    Next
    INDEX
    Explanations

    text related to policing and legal documents

    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
    الإنجليزية
    -0.81
     bezeichneter
    -0.67
    󠁢
    -0.65
    ticons
    -0.58
    UnsafeEnabled
    -0.58
    ậc
    -0.57
    essions
    -0.57
     gehörte
    -0.56
    ciona
    -0.55
     contado
    -0.55
    POSITIVE LOGITS
    SequentialGroup
    0.50
    kannt
    0.49
     emis
    0.46
     становника
    0.45
    })()
    0.45
    chemise
    0.45
     interpol
    0.43
    ViewById
    0.43
    ANDUM
    0.42
     policies
    0.42
    Activations Density 0.182%

    No Known Activations