© 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. 3-RES-MATRYOSHKA-DC
    7. 1863
    Prev
    Next
    INDEX
    Explanations

    the word "custom" and words that often appear near "custom" like "built" and sometimes numerical digits

    oai_token-act-pair · gemini-2.0-flash
    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
    AddTagHelper
    -0.82
    contentLoaded
    -0.82
    DockStyle
    -0.81
    ELTS
    -0.81
    antaranya
    -0.80
    цездатний
    -0.78
    SpringBootTest
    -0.78
    TableBody
    -0.77
    slidesPer
    -0.77
    quels
    -0.76
    POSITIVE LOGITS
     custom
    3.28
     Custom
    3.19
    custom
    3.08
    Custom
    3.05
     CUSTOM
    2.78
    CUSTOM
    2.61
     customized
    2.36
     customised
    2.20
     Customized
    2.13
     customize
    2.08
    Activations Density 0.033%

    No Known Activations