© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 725
    Prev
    Next
    INDEX
    Explanations

    newline followed by a single digit number followed by a period

    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.22.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.22.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
    enterOuterAlt
    -0.69
    Calculate
    -0.68
    ModelAdmin
    -0.67
     termica
    -0.65
    calculate
    -0.65
     calculate
    -0.64
     Calculate
    -0.63
     &___
    -0.63
     calculating
    -0.59
    calc
    -0.57
    POSITIVE LOGITS
     let
    1.51
     Let
    1.25
    Let
    1.16
    let
    1.05
     LET
    1.04
     letting
    0.94
     suppose
    0.91
     lets
    0.89
    LET
    0.80
    letting
    0.75
    Activations Density 0.085%

    No Known Activations