© 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. 29804
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scoring or ranking performance metrics

    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
     '\\;'
    -0.70
    MockMvc
    -0.66
    DockStyle
    -0.65
     volontaire
    -0.64
    ftar
    -0.63
    ronyms
    -0.62
    ijakan
    -0.61
     nomine
    -0.60
     doPost
    -0.60
    transQ
    -0.60
    POSITIVE LOGITS
     án
    0.57
     feeling
    0.52
     lu
    0.46
     felt
    0.45
    Carriera
    0.45
     rank
    0.44
     Bag
    0.44
     Sal
    0.43
    ])->
    0.43
     ris
    0.43
    Activations Density 0.137%

    No Known Activations