© 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. 876
    Prev
    Next
    INDEX
    Explanations

    decimal points in numbers within scientific results

    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
    ebvre
    -0.50
     FishBase
    -0.49
    anskje
    -0.46
    onoi
    -0.44
    jooq
    -0.44
    HomeAsUp
    -0.44
    DebuggerStep
    -0.44
     Anſ
    -0.44
    oa̍t
    -0.44
     geval
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.68
    ticon
    0.64
     propOrder
    0.61
     resourceCulture
    0.60
    //{
    0.60
    GEBURTSDATUM
    0.59
    AndEndTag
    0.57
    #
    0.57
    رشف
    0.56
    EDEFAULT
    0.55
    Activations Density 0.220%

    No Known Activations