© 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. 16701
    Prev
    Next
    INDEX
    Explanations

    equal signs or expressions of equivalence in mathematical 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
    +:+
    -0.81
     Balt
    -0.70
     ?',
    -0.69
    ();)
    -0.68
     Normdatei
    -0.68
    ]")]
    -0.68
     ſeveral
    -0.67
     itſelf
    -0.65
     Aper
    -0.65
    исленность
    -0.65
    POSITIVE LOGITS
    IVEREF
    0.52
    حياتها
    0.46
     olvides
    0.45
     her
    0.44
     god
    0.41
     Савезне
    0.40
    jdbc
    0.40
    WriteBarrier
    0.39
     God
    0.39
    charCodeAt
    0.39
    Activations Density 0.018%

    No Known Activations