© 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. 5988
    Prev
    Next
    INDEX
    Explanations

    patterns of special characters and encoded mathematical syntax

    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
     الحره
    -0.71
    }}}$
    -0.68
    \{\\
    -0.65
    })}$
    -0.65
    entary
    -0.62
    autogui
    -0.60
    })]
    -0.60
    })$}
    -0.59
    }\]
    -0.59
    Personendaten
    -0.59
    POSITIVE LOGITS
    interopRequire
    0.66
    WebVitals
    0.58
    ToBounds
    0.57
    ευ
    0.55
    Fprintf
    0.52
    toHaveBeenCalled
    0.50
    êques
    0.50
    EndContext
    0.50
    makeText
    0.50
    AndroidJUnit
    0.49
    Activations Density 2.485%

    No Known Activations