© 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. 18-RES-MATRYOSHKA-DC
    7. 1055
    Prev
    Next
    INDEX
    Explanations

    the word "sample" followed by a noun

    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.18.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.18.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
    PointerException
    -0.64
    StoryboardSegue
    -0.60
     }^{-
    -0.56
     defaultstate
    -0.56
    <?,
    -0.55
    Архівовано
    -0.55
    Aiheesta
    -0.55
     }}^{\
    -0.54
    oforte
    -0.54
    ).-
    -0.54
    POSITIVE LOGITS
     Samples
    1.41
    samples
    1.30
     samples
    1.28
    Samples
    1.25
     SAMPLE
    1.20
     Sample
    1.17
    SAMPLE
    1.15
    Sample
    1.09
     SAMPLES
    1.01
     Samp
    1.00
    Activations Density 0.129%

    No Known Activations