© 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. 2222
    Prev
    Next
    INDEX
    Explanations

    terms related to progress or advancement in various contexts

    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
    didSet
    -1.09
    ibrill
    -0.97
    rillation
    -0.89
     Jha
    -0.88
    tréal
    -0.86
     Poole
    -0.86
    ajur
    -0.85
    anasia
    -0.81
    usitis
    -0.80
     giuri
    -0.80
    POSITIVE LOGITS
     Forward
    1.44
    Forward
    1.41
    forward
    1.40
     forward
    1.37
     FORWARD
    1.36
     advances
    1.33
     advance
    1.27
     Advance
    1.27
    Advance
    1.24
     Advances
    1.24
    Activations Density 0.126%

    No Known Activations