© 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. 5864
    Prev
    Next
    INDEX
    Explanations

    references to configuration parameters or settings

    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
     particularly
    -0.60
    VersionUID
    -0.59
     especially
    -0.55
     trương
    -0.53
    Definitions
    -0.52
     useStyles
    -0.52
    NewGuid
    -0.51
     regards
    -0.50
     particular
    -0.50
    particularly
    -0.48
    POSITIVE LOGITS
     Specified
    2.41
     specified
    2.36
    specified
    2.33
     specify
    2.22
     Specify
    2.19
    pecified
    2.08
     specifies
    2.05
    Specified
    1.97
     specifying
    1.91
     specification
    1.82
    Activations Density 0.012%

    No Known Activations