© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16470
    Prev
    Next
    INDEX
    Explanations

    references to hyperlinks and URLs

    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
    kür
    -0.59
     Pease
    -0.56
     Audiodateien
    -0.56
     مرئيه
    -0.56
    Източници
    -0.55
    uba
    -0.53
     joaat
    -0.53
    unos
    -0.53
    record
    -0.52
     mineures
    -0.52
    POSITIVE LOGITS
    RenderAtEndOf
    0.84
    IntoConstraints
    0.76
    GIVEREF
    0.67
    instancetype
    0.59
    QMetaType
    0.58
    GEBURTSDATUM
    0.57
    VersionUID
    0.57
    ьаж
    0.56
     OMITBAD
    0.56
    XmlSchema
    0.56
    Activations Density 0.036%

    No Known Activations