© 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. 718
    Prev
    Next
    INDEX
    Explanations

    the letter "G" followed by other characters such as numbers and hyphens

    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
    wieś
    -0.73
    ValueStyle
    -0.72
     @"/
    -0.68
     dAtA
    -0.65
    esModule
    -0.64
    GEBURTSDATUM
    -0.63
     }{@
    -0.63
     /\.
    -0.62
     viewType
    -0.61
     AssemblyTitle
    -0.60
    POSITIVE LOGITS
    aus
    0.53
    ah
    0.50
     oog
    0.50
     démocratique
    0.45
     job
    0.45
    listening
    0.44
     Adventures
    0.43
    ic
    0.43
    zipped
    0.43
    localisation
    0.42
    Activations Density 0.505%

    No Known Activations