© 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. 2-RES-MATRYOSHKA-DC
    7. 7348
    Prev
    Next
    INDEX
    Explanations

    mentions of soil nitrogen components and their relationships

    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
     umane
    -0.57
     consec
    -0.54
     Affiliations
    -0.49
    InstrumentedTest
    -0.49
     reverse
    -0.48
    okka
    -0.48
    malle
    -0.47
    reverse
    -0.46
     AssemblyCulture
    -0.46
     AssemblyTitle
    -0.46
    POSITIVE LOGITS
    DebuggerNonUser
    0.67
    haustible
    0.65
     carbs
    0.61
    Phosphorus
    0.59
     NSCoder
    0.59
     HttpHeaders
    0.58
     Phosphorus
    0.56
    FieldNumber
    0.56
     phosphorus
    0.55
     getItemId
    0.55
    Activations Density 0.791%

    No Known Activations