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. 31070
    Prev
    Next
    INDEX
    Explanations

    acronyms in the format of "CN" followed by another letter

    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
    twimg
    -0.63
     Kass
    -0.63
     col
    -0.60
     Compostela
    -0.60
     Hawke
    -0.59
    Πε
    -0.59
    Kond
    -0.59
    Kass
    -0.58
     Kond
    -0.58
    Bson
    -0.58
    POSITIVE LOGITS
     CN
    1.55
    CN
    1.46
    cn
    1.20
     cn
    1.18
     cyanide
    1.09
     Cn
    1.03
     CNRS
    0.96
     CNBC
    0.96
    Cn
    0.93
     Cuen
    0.88
    Activations Density 0.009%

    No Known Activations