© 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. 6829
    Prev
    Next
    INDEX
    Explanations

    references to the mathematical concept of 'in,' possibly related to elements being contained within a set or space

    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
    geq
    -0.92
    iffance
    -0.88
    leq
    -0.85
    <<<<
    -0.79
    DeleteBehavior
    -0.79
    IntoConstraints
    -0.78
    leqslant
    -0.77
    leqq
    -0.75
    neq
    -0.75
     addSubview
    -0.75
    POSITIVE LOGITS
    in
    1.16
    ∈
    0.89
    IN
    0.84
    inc
    0.66
    mathcal
    0.63
     ∈
    0.56
    an
    0.52
     espon
    0.52
    inz
    0.51
    ê
    0.50
    Activations Density 0.039%

    No Known Activations