© 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. 601
    Prev
    Next
    INDEX
    Explanations

    words that describe something abstract

    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
     etc
    -0.75
     Etc
    -0.65
    OGND
    -0.62
     plus
    -0.60
     while
    -0.59
    },[])
    -0.58
    mybatisplus
    -0.58
     THEN
    -0.58
     then
    -0.56
     puis
    -0.56
    POSITIVE LOGITS
     puisqu
    1.02
     inasmuch
    1.02
     puisque
    0.96
     insofar
    0.91
     إذ
    0.87
     poiché
    0.84
     hiszen
    0.84
    :
    0.82
    pues
    0.82
     insom
    0.80
    Activations Density 2.345%

    No Known Activations