© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5629
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols commonly found in equations

    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
     —
    -0.75
    ”
    -0.73
     “
    -0.71
    <sup>
    -0.67
    GraphicsUnit
    -0.65
     Wilk
    -0.63
    —
    -0.62
     of
    -0.60
    McKin
    -0.60
     Morgan
    -0.59
    POSITIVE LOGITS
     }}$}
    1.27
    '}}
    1.17
    ...}
    1.10
    "}
    1.09
     photolibrary
    1.09
     }}
    1.07
    ?}
    1.07
     CURIAM
    1.05
    "}}
    1.04
    '}
    1.03
    Activations Density 0.422%

    No Known Activations