© 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. 1-RES-MATRYOSHKA-DC
    7. 709
    Prev
    Next
    INDEX
    Explanations

    references to fundamental principles or core knowledge

    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
    ]!='
    -0.63
    tvguidetime
    -0.59
    Politique
    -0.56
    äinen
    -0.56
    mitian
    -0.55
     BASED
    -0.54
    EndTag
    -0.52
    arget
    -0.51
    ÁF
    -0.51
    yant
    -0.51
    POSITIVE LOGITS
     basic
    4.47
    basic
    4.34
    Basic
    4.19
     Basic
    4.19
     BASIC
    3.45
    BASIC
    3.42
     basics
    3.08
     básico
    3.03
     básica
    3.00
     básicos
    2.73
    Activations Density 0.196%

    No Known Activations