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. 30813
    Prev
    Next
    INDEX
    Explanations

    tokens when they are commas or the word 'words'

    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
     löytyy
    -0.42
    ne
    -0.40
     løpet
    -0.40
     vocale
    -0.40
    za
    -0.39
     comedor
    -0.39
     csoport
    -0.39
     líqu
    -0.39
     raggiunto
    -0.38
    กระท
    -0.37
    POSITIVE LOGITS
    ngdoc
    1.02
     Савезне
    0.98
     tartalomajánló
    0.88
    Portale
    0.87
     فريبيس
    0.84
    +#+#
    0.84
    AccessorTable
    0.81
    httphttps
    0.81
    ագրություններ
    0.80
    WindowConstants
    0.79
    Activations Density 0.021%

    No Known Activations