© 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. 24-RES-MATRYOSHKA-DC
    7. 1205
    Prev
    Next
    INDEX
    Explanations

    chemical formulas

    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
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.52
    razine
    -0.47
    writeFieldEnd
    -0.44
    abetes
    -0.40
    eneuve
    -0.39
    álna
    -0.39
    ěst
    -0.38
    grà
    -0.38
    GEBURTSDATUM
    -0.38
    protoimpl
    -0.38
    POSITIVE LOGITS
     o
    1.38
     O
    1.35
    O
    1.34
    o
    1.13
    オ
    1.13
    Ｏ
    1.05
    โอ
    1.05
     OC
    1.00
     OA
    0.99
     OL
    0.97
    Activations Density 3.014%

    No Known Activations