© 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. 8641
    Prev
    Next
    INDEX
    Explanations

    references to bloggers or blogging activity

    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
    LLocation
    -0.70
    RLock
    -0.60
    ranton
    -0.59
    TreeMap
    -0.59
    ījum
    -0.59
    Eksteraj
    -0.57
    BindView
    -0.55
    ISupport
    -0.55
     Gefähr
    -0.55
    EdgeInsets
    -0.53
    POSITIVE LOGITS
    blogger
    1.45
    Blogger
    1.30
     Blogger
    1.17
     blogger
    1.00
    XmlAccessorType
    0.80
     defaultstate
    0.73
     bloggers
    0.71
    MessageOf
    0.66
    Obrázky
    0.61
    GEBURTSDATUM
    0.60
    Activations Density 0.000%

    No Known Activations