© 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. 749
    Prev
    Next
    INDEX
    Explanations

    phrases describing how easily things are going

    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
     незавершена
    -0.66
    erweise
    -0.65
    uxxxx
    -0.63
    lccn
    -0.60
    ISCHE
    -0.59
    StreetMap
    -0.58
    mybatisplus
    -0.57
    esez
    -0.57
     assoluto
    -0.57
    ötzlich
    -0.56
    POSITIVE LOGITS
     well
    2.88
    well
    1.95
     WELL
    1.80
    Well
    1.72
     Well
    1.72
    WELL
    1.55
     hyvin
    1.55
     better
    1.52
     nicely
    1.49
     excellently
    1.49
    Activations Density 1.314%

    No Known Activations