© 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. 22-RES-MATRYOSHKA-DC
    7. 1565
    Prev
    Next
    INDEX
    Explanations

    events that have happened for the first time

    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.22.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.22.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
    CppMethod
    -0.58
    thalle
    -0.48
    simpleType
    -0.47
     Adic
    -0.46
    RenderAtEndOf
    -0.44
    sizeCache
    -0.44
     protoimpl
    -0.44
    Trey
    -0.44
     Audiodateien
    -0.43
    ozof
    -0.42
    POSITIVE LOGITS
     spacecraft
    1.17
     NASA
    1.16
     Earth
    1.13
     orbit
    1.12
     planet
    1.11
     orbiting
    1.07
     moon
    1.07
    NASA
    1.06
     Mars
    1.05
     earth
    1.05
    Activations Density 1.421%

    No Known Activations