© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12007
    Prev
    Next
    INDEX
    Explanations

    specific protein identifiers or related technical terminology

    oai_token-act-pair · gpt-4.1-nano
    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
    ado
    -1.13
    aton
    -1.02
    atos
    -1.01
    atus
    -0.98
    ADO
    -0.95
    atum
    -0.94
    ados
    -0.93
    ADOS
    -0.82
    atu
    -0.74
    migrationBuilder
    -0.74
    POSITIVE LOGITS
    ato
    1.30
     Chwiliwch
    0.70
     ['./
    0.62
    essoal
    0.61
    fjspx
    0.59
     navideñas
    0.58
     contextLoads
    0.57
    دانشنامهٔ
    0.57
     Hardly
    0.57
     виправивши
    0.56
    Activations Density 0.001%

    No Known Activations