© 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. 32566
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "head"

    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
     +
    -0.50
     "
    -0.46
     de
    -0.43
     le
    -0.43
    setAction
    -0.42
     et
    -0.42
    önster
    -0.41
     current
    -0.40
    antd
    -0.40
    .
    -0.40
    POSITIVE LOGITS
     nakalista
    0.98
     BoxDecoration
    0.90
     Monfieur
    0.89
    SequentialGroup
    0.88
    IsContent
    0.85
     myſelf
    0.85
     صوتيه
    0.84
    XmlAccessorType
    0.84
     whoſe
    0.83
     كومونز
    0.82
    Activations Density 0.001%

    No Known Activations