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. 12039
    Prev
    Next
    INDEX
    Explanations

    structure and formatting in JSON data

    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
     envers
    -0.77
    ,:),
    -0.75
    *}[
    -0.74
    })),
    -0.73
    [::-
    -0.72
    :].
    -0.72
     GridView
    -0.71
    ])),
    -0.70
     Fitzpatrick
    -0.69
    ########.
    -0.69
    POSITIVE LOGITS
     rowspan
    0.74
     initWithFrame
    0.71
    greenrobot
    0.69
    tréal
    0.68
    tmpl
    0.68
     vd
    0.67
     Eud
    0.66
    sid
    0.65
     yd
    0.65
     Caus
    0.65
    Activations Density 0.045%

    No Known Activations