© 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. 12-RES-MATRYOSHKA-DC
    7. 23780
    Prev
    Next
    INDEX
    Explanations

    numerical data and mathematical expressions related to fractional derivatives and splines

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     or
    -0.58
     B
    -0.56
     di
    -0.53
     can
    -0.50
     che
    -0.50
     b
    -0.49
     in
    -0.46
     be
    -0.46
     E
    -0.45
     te
    -0.45
    POSITIVE LOGITS
     myſelf
    1.06
     purpoſe
    1.05
     Majefty
    1.05
     Theſe
    1.05
     itſelf
    1.04
     greateſt
    1.02
     ſtand
    1.00
     ſche
    0.98
     himſelf
    0.96
     Houſe
    0.96
    Activations Density 0.091%

    No Known Activations