© 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
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 6284
    Prev
    Next
    INDEX
    Explanations

    lines of code involving bitwise negation or tilde symbols

    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
    setVerticalGroup
    -0.94
     שוליים
    -0.93
    makeConstraints
    -0.89
     lenker
    -0.88
    IntoConstraints
    -0.86
    }());
    -0.82
    dymyr
    -0.80
     GenerationType
    -0.80
     '\\;'
    -0.79
     */;
    -0.78
    POSITIVE LOGITS
     ~
    1.90
     (~
    1.37
    (~
    1.25
     ~(
    1.23
    ~
    1.13
    /~
    1.12
     "~
    1.02
    ,~
    1.02
    ~\
    0.96
     '~
    0.94
    Activations Density 0.053%

    No Known Activations