© 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. 1-RES-MATRYOSHKA-DC
    7. 335
    Prev
    Next
    INDEX
    Explanations

    references to the word "from" in text

    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
    expandindo
    -0.86
    iertas
    -0.77
     autorytatywna
    -0.77
    fjspx
    -0.71
     kasarigan
    -0.70
    invokeLater
    -0.70
    complexContent
    -0.69
    geois
    -0.68
     COE
    -0.63
    ofür
    -0.63
    POSITIVE LOGITS
     from
    3.41
    from
    3.08
     FROM
    3.06
    FROM
    2.78
     From
    2.77
    From
    2.73
     från
    2.31
     dari
    2.17
     từ
    2.14
    จาก
    2.13
    Activations Density 0.615%

    No Known Activations