© 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. 3633
    Prev
    Next
    INDEX
    Explanations

    references to the name "Ho," specifically "Ho" or "Ho" with capitalization, indicating it is looking for variations of that particular name

    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
    хьтан
    -0.69
    HtmlAttribute
    -0.68
    hka
    -0.65
    Географи
    -0.61
     تانيه
    -0.60
    ngrx
    -0.60
     Yarm
    -0.60
    GEBURTSDATUM
    -0.60
    
    -0.60
     Hyde
    -0.59
    POSITIVE LOGITS
     ho
    3.20
     Ho
    3.17
    Ho
    3.16
    ho
    2.84
     HO
    2.34
    HO
    2.30
     holographic
    1.40
    ホ
    1.38
     hopping
    1.37
     hopper
    1.34
    Activations Density 0.126%

    No Known Activations