© 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. 21
    Prev
    Next
    INDEX
    Explanations

    programming source code

    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
    
    -1.08
    tershire
    -1.04
    ianum
    -1.02
    igenous
    -1.02
    æus
    -1.02
    ">↑↑↑</
    -1.02
    ◲
    -1.02
    <0x1D>
    -1.01
    <0x20>
    -1.01
    <0x2A>
    -1.01
    POSITIVE LOGITS
     wikipagina
    -0.17
     varandra
    -0.17
     étoient
    -0.18
     stället
    -0.20
     vägen
    -0.24
     anún
    -0.25
     avoient
    -0.26
     feroit
    -0.30
     engraçadas
    -0.31
     vérit
    -0.32
    Activations Density 26.278%

    No Known Activations