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. 31114
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating subjective perception or insincerity.

    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
    ագրություններ
    -0.65
    NamedQueries
    -0.62
    انجليز
    -0.58
     BIBLIO
    -0.56
    %";
    -0.56
     Efq
    -0.54
    ర్య
    -0.54
     lenker
    -0.53
     GoogleFonts
    -0.53
    %");
    -0.53
    POSITIVE LOGITS
     deepcopy
    0.61
     apparente
    0.60
    ficial
    0.57
     Мексичка
    0.55
     vitro
    0.54
     خارجية
    0.53
     estekak
    0.53
     pretended
    0.52
    rician
    0.51
    žių
    0.51
    Activations Density 0.098%

    No Known Activations