© 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. 4032
    Prev
    Next
    INDEX
    Explanations

    instances of the term "IF" with high confidence

    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
     AssemblyTitle
    -0.81
     betweenstory
    -0.80
    IsContent
    -0.79
    InjectAttribute
    -0.78
     NSCoder
    -0.73
    ArgsConstructor
    -0.72
     onOptions
    -0.70
     Wiktionnaire
    -0.68
     ModelExpression
    -0.68
    }]);
    -0.67
    POSITIVE LOGITS
    IF
    2.88
     IF
    1.99
    IFF
    1.23
    ifs
    1.19
    IFS
    1.11
    IFT
    1.05
    NIF
    1.00
    TIF
    0.97
    iff
    0.95
    ife
    0.91
    Activations Density 0.031%

    No Known Activations