Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16840
    Prev
    Next
    INDEX
    Explanations

    references to hip-related surgical procedures and components

    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
    igneurs
    -0.67
     Amman
    -0.66
    Susie
    -0.66
     splinter
    -0.65
     Stamps
    -0.64
     Istri
    -0.64
    aim
    -0.63
     Genève
    -0.63
    .='
    -0.63
    angliski
    -0.63
    POSITIVE LOGITS
     hip
    1.20
     hips
    1.14
     Hip
    1.12
    Hip
    1.09
     pelvis
    0.95
     femoral
    0.90
     femur
    0.88
    hip
    0.87
    ReusableCell
    0.82
     thigh
    0.81
    Activations Density 0.008%

    No Known Activations