© 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. 962
    Prev
    Next
    INDEX
    Explanations

    statements or sections expressing the primary aim or objective

    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
     due
    -0.59
    brock
    -0.58
    Requested
    -0.56
    DECREF
    -0.53
    HasMaxLength
    -0.53
    mybatisplus
    -0.52
    assertRaises
    -0.52
    ResponseEntity
    -0.51
    NSNotification
    -0.51
     Familienname
    -0.50
    POSITIVE LOGITS
     purpose
    4.81
     Purpose
    4.31
    purpose
    4.19
    Purpose
    4.13
     PURPOSE
    3.91
     purposes
    3.83
    PURPOSE
    3.39
     Purposes
    3.33
    purposes
    3.19
     propósito
    2.75
    Activations Density 0.275%

    No Known Activations