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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 9-RES-MATRYOSHKA-DC
    4. 16744
    Prev
    Next
    INDEX
    Explanations

    mathematical notation indicating set membership

    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
     Autónoma
    -0.70
    InjectAttribute
    -0.66
     Italijani
    -0.65
     newBuilder
    -0.64
    aternion
    -0.61
     Roskov
    -0.60
    triangleq
    -0.59
    gnat
    -0.59
    ciutto
    -0.59
     experimentally
    -0.58
    POSITIVE LOGITS
     kasarigan
    0.54
    ]")]
    0.54
    rungsseite
    0.52
    帖最后由
    0.47
    новништво
    0.47
     dummy
    0.44
    dummy
    0.43
     are
    0.43
     hall
    0.42
    StandardCharsets
    0.42
    Activations Density 0.024%

    No Known Activations