© 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. 12-RES-MATRYOSHKA-DC
    7. 32197
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "final" in various contexts, indicating a focus on finality or completion

    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
     neceffary
    -0.89
     itſelf
    -0.84
     themſelves
    -0.83
     himſelf
    -0.82
     Efq
    -0.81
     myſelf
    -0.81
     Jefus
    -0.80
     fufficient
    -0.79
     تضيفلها
    -0.76
     occafion
    -0.76
    POSITIVE LOGITS
     final
    0.63
     نها
    0.58
     derro
    0.58
    Sprintf
    0.57
     Staf
    0.57
    tvar
    0.56
     Final
    0.53
    appcompat
    0.52
    BeforeClass
    0.52
     déb
    0.52
    Activations Density 0.005%

    No Known Activations