© 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. 24-RES-MATRYOSHKA-DC
    7. 1404
    Prev
    Next
    INDEX
    Explanations

    numerical chemical measurements, especially related to *ortho* and *para* positions and ppm

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     lenker
    -0.77
    ритори
    -0.68
    rungsseite
    -0.66
    ThroughAttribute
    -0.62
     onOptions
    -0.60
    Története
    -0.58
    TintMode
    -0.57
    msgSender
    -0.56
     comisión
    -0.55
    ksikon
    -0.54
    POSITIVE LOGITS
    ~,
    0.55
    ~:
    0.53
    ~
    0.53
    ~.
    0.49
    #+#
    0.49
    *~
    0.48
     numerus
    0.47
    Ծանոթ
    0.47
     broad
    0.46
    ~*~
    0.46
    Activations Density 0.103%

    No Known Activations