© 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. 22778
    Prev
    Next
    INDEX
    Explanations

    names, specifically identifying and counting occurrences related to the term "Gerda."

    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
    Negative Logits
     Havel
    -0.85
     Adder
    -0.82
     Shakspeare
    -0.82
     faſt
    -0.81
     Shaksp
    -0.81
     Diſ
    -0.81
     '+':
    -0.81
     adder
    -0.80
    ніципалі
    -0.80
    igneurs
    -0.80
    POSITIVE LOGITS
     Ger
    1.47
    Ger
    1.40
     ger
    1.30
     Gerber
    1.20
     GER
    1.08
     germs
    0.93
     Gerardo
    0.93
     Gertrude
    0.85
     Roh
    0.80
    ger
    0.79
    Activations Density 0.005%

    No Known Activations