© 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. 18522
    Prev
    Next
    INDEX
    Explanations

    terms related to root mean square (RMS) calculations

    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
     jc
    -0.75
     Vey
    -0.72
     ATR
    -0.70
    FieldNumber
    -0.70
     :</
    -0.69
     Passer
    -0.69
     Refle
    -0.69
     Pola
    -0.69
     Laurens
    -0.69
     SANS
    -0.68
    POSITIVE LOGITS
    rm
    1.20
     RM
    1.15
     Erm
    1.13
    RM
    1.09
     rm
    1.07
    Erm
    0.98
     Malik
    0.76
    Rm
    0.74
    ษัท
    0.73
    rašymas
    0.69
    Activations Density 0.016%

    No Known Activations