© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 422
    Prev
    Next
    INDEX
    Explanations

    the word "if" followed by a pronoun

    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
    migrationBuilder
    -0.70
    ymce
    -0.66
     يتيمه
    -0.64
     Αρχ
    -0.63
     készült
    -0.62
     Lindley
    -0.62
    adda
    -0.60
    resents
    -0.60
    Heraus
    -0.60
    rmt
    -0.59
    POSITIVE LOGITS
     if
    2.83
    if
    2.39
     If
    2.20
    If
    2.06
     jika
    1.89
     IF
    1.85
     если
    1.84
     nếu
    1.80
     dacă
    1.78
     hvis
    1.75
    Activations Density 0.826%

    No Known Activations