© 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. 781
    Prev
    Next
    INDEX
    Explanations

    the keyword 'const' often used in software development source code

    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
    /**
    -0.81
    providedIn
    -0.80
     <<<<<<<<<<<<<<
    -0.69
    iostream
    -0.68
    stdc
    -0.65
    stdafx
    -0.65
     XCTest
    -0.65
    riwal
    -0.63
     Meda
    -0.63
     ويكيميديا
    -0.62
    POSITIVE LOGITS
     const
    1.38
    const
    1.34
     Const
    1.26
    Const
    1.16
    CONST
    0.94
     CONST
    0.87
     Constan
    0.87
     Constable
    0.85
     constriction
    0.75
     canst
    0.73
    Activations Density 0.062%

    No Known Activations