© 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. 0-RES-MATRYOSHKA-DC
    7. 11021
    Prev
    Next
    INDEX
    Explanations

    the presence of specific identifiers related to the term "Ih" or its variants

    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
    stdafx
    -0.54
    :///
    -0.54
    haft
    -0.54
    DataAnnotations
    -0.54
    likat
    -0.53
    ípio
    -0.52
     cím
    -0.52
    aset
    -0.52
     &___
    -0.52
    iecie
    -0.51
    POSITIVE LOGITS
    ih
    3.67
    IH
    2.03
     ih
    1.49
     Ih
    1.15
    Ih
    1.12
    ihe
    1.02
     IH
    1.00
    tih
    0.93
    ihin
    0.87
     demografica
    0.67
    Activations Density 0.001%

    No Known Activations