© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30947
    Prev
    Next
    INDEX
    Explanations

    references to the name "Hor" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ruto
    -0.75
    OCCURRED
    -0.69
     Abdulla
    -0.68
    Bridges
    -0.68
    uille
    -0.67
     loadData
    -0.66
    MigrationBuilder
    -0.66
    rdida
    -0.66
    Gail
    -0.66
    raad
    -0.65
    POSITIVE LOGITS
     Hor
    1.33
    Hor
    1.31
     Horne
    1.28
     Horowitz
    1.19
     Horner
    1.15
     hor
    1.11
     Horacio
    1.09
     horizon
    1.07
     HOR
    1.06
    Horst
    1.05
    Activations Density 0.006%

    No Known Activations