© 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. 6-RES-MATRYOSHKA-DC
    7. 1195
    Prev
    Next
    INDEX
    Explanations

    text related to automated technology and artificial intelligence

    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
    endsection
    -0.90
    SourceChecksum
    -0.69
    )"),
    -0.68
    )")
    -0.65
     Thule
    -0.65
    +"/"+
    -0.60
     bezeichneter
    -0.60
    hibernate
    -0.59
    ::::::::
    -0.59
     shippuden
    -0.59
    POSITIVE LOGITS
     robot
    1.41
     Robots
    1.32
     robots
    1.30
     Robot
    1.26
    Robots
    1.26
    Robot
    1.22
     robotic
    1.21
    robot
    1.19
     automated
    1.14
     Robotic
    1.10
    Activations Density 0.760%

    No Known Activations