© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5204
    Prev
    Next
    INDEX
    Explanations

    form input elements based on their type attribute

    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
    principalColumn
    -1.05
    findpost
    -0.92
     ―――――
    -0.89
     >=",
    -0.85
    ^(@)
    -0.84
    IUrlHelper
    -0.83
    Chham
    -0.82
    afone
    -0.81
     Jefus
    -0.81
    RegressionTest
    -0.76
    POSITIVE LOGITS
    type
    0.63
     им
    0.44
     peanuts
    0.43
    ,
    0.43
     Later
    0.42
    id
    0.42
     követ
    0.42
    '
    0.41
     szüks
    0.41
    x
    0.41
    Activations Density 0.139%

    No Known Activations