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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13794
    Prev
    Next
    INDEX
    Explanations

    references to the measurement of purity or quality of a sample or substance

    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
    abestanden
    -0.75
    IndentedString
    -0.63
    addOn
    -0.58
    υνα
    -0.57
    awtextra
    -0.57
     виправивши
    -0.56
    躇
    -0.54
     beginnetje
    -0.54
    Hozzáférés
    -0.53
     InputDecoration
    -0.53
    POSITIVE LOGITS
     purity
    3.28
     Purity
    2.66
    Purity
    2.28
     pureza
    1.91
    urity
    1.08
     purer
    1.02
     impurity
    0.94
     impurities
    0.90
     purest
    0.84
     chastity
    0.73
    Activations Density 0.000%

    No Known Activations