© 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. 1217
    Prev
    Next
    INDEX
    Explanations

    the word "up" followed by the word "to"

    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
    DebuggerNonUser
    -0.70
     AssemblyCompany
    -0.66
    WebServlet
    -0.63
    ]--;
    -0.60
    glTexCoord
    -0.60
    antaine
    -0.59
     Winaray
    -0.57
     Tela
    -0.57
     Hache
    -0.57
    пиона
    -0.56
    POSITIVE LOGITS
     UP
    0.92
     Up
    0.92
     up
    0.84
    Up
    0.82
     Ups
    0.79
    wards
    0.76
    Ups
    0.76
     ups
    0.75
    UP
    0.73
    ups
    0.73
    Activations Density 0.618%

    No Known Activations