© 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. 837
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving, possibly as an action or deed

    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
    DrawerLayout
    -0.68
     betweenstory
    -0.64
    ftagPool
    -0.59
    hasMoreElements
    -0.59
    norsk
    -0.57
     виправивши
    -0.56
    انيف
    -0.56
     beginnetje
    -0.54
    uxxxx
    -0.52
     nakalista
    -0.52
    POSITIVE LOGITS
     rise
    1.34
     birth
    1.06
     away
    1.05
    aways
    0.90
    away
    0.89
     credence
    0.85
    rise
    0.83
     preference
    0.80
     priority
    0.77
    birth
    0.76
    Activations Density 0.715%

    No Known Activations