© 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. 19843
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'rhino' and its variations

    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
     Marlow
    -0.66
     rato
    -0.64
     fru
    -0.62
     beren
    -0.57
     Matilda
    -0.56
    Ro
    -0.55
     spre
    -0.54
     sfor
    -0.54
     Futura
    -0.54
     Topeka
    -0.53
    POSITIVE LOGITS
     Rh
    1.40
    Rh
    1.40
     rh
    1.36
     RH
    1.31
     Rhin
    1.29
     Rhi
    1.19
    RH
    1.16
     Rhodes
    1.16
    rh
    1.12
    Rhin
    1.12
    Activations Density 0.026%

    No Known Activations