© 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. 24290
    Prev
    Next
    INDEX
    Explanations

    phrases related to progression and advancement

    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
    Captor
    -0.69
    httphttps
    -0.60
    ViewChild
    -0.59
    Portály
    -0.59
     KGB
    -0.57
    BagConstraints
    -0.56
    CreateMap
    -0.56
     BoxDecoration
    -0.56
    ξύ
    -0.55
    estrado
    -0.55
    POSITIVE LOGITS
    SourceChecksum
    0.57
     án
    0.54
     pass
    0.54
    Ignore
    0.54
     proceeding
    0.53
     proceed
    0.53
     ignoring
    0.52
     PROCEED
    0.51
     passed
    0.49
     ignored
    0.49
    Activations Density 0.110%

    No Known Activations