Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 15384
    Prev
    Next
    INDEX
    Explanations

    function calls or method signatures that contain parentheses

    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
     soi
    -0.55
     kasarigan
    -0.53
    گانه
    -0.52
     ég
    -0.51
    sprozess
    -0.51
     connexes
    -0.49
    таратура
    -0.49
    rschein
    -0.48
     Polres
    -0.48
    tvguidetime
    -0.48
    POSITIVE LOGITS
    })->
    0.83
    AnchorStyles
    0.80
    ?')
    0.73
     Meksiku
    0.72
    })),
    0.72
    &)
    0.71
    >")
    0.70
    )"),
    0.70
    -),
    0.69
    }`).
    0.69
    Activations Density 0.002%

    No Known Activations