Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31082
    Prev
    Next
    INDEX
    Explanations

    opening square brackets preceded by a dollar sign

    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
    <sup>
    -0.70
    5
    -0.66
    y
    -0.62
    ്
    -0.60
    o
    -0.60
    e
    -0.59
    g
    -0.59
    ٰ
    -0.58
     spal
    -0.58
    #
    -0.58
    POSITIVE LOGITS
     themſelves
    1.04
     myſelf
    0.98
     purpoſe
    0.96
    riors
    0.94
     himſelf
    0.90
    WebServlet
    0.90
     DbContext
    0.89
     assent
    0.87
     pleaſure
    0.86
     ConstraintSet
    0.85
    Activations Density 0.006%

    No Known Activations