© 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. 10297
    Prev
    Next
    INDEX
    Explanations

    statements about assumptions or perceptions regarding an unspecified subject's significance or meaning

    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
     للاسماء
    -0.62
     فريبيس
    -0.59
    InputBorder
    -0.57
     privile
    -0.56
    ]));
    -0.56
     يتيمه
    -0.56
    WriteTagHelper
    -0.55
    astéroïdes
    -0.55
    NameInMap
    -0.54
     lucy
    -0.52
    POSITIVE LOGITS
    bleshooting
    0.63
    ⓧ
    0.63
    Manbalar
    0.52
     useStyles
    0.51
    Personendaten
    0.49
     henkil
    0.49
    ografija
    0.48
     AsyncTask
    0.48
    StackNavigator
    0.47
    Encoded
    0.47
    Activations Density 0.048%

    No Known Activations