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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19858
    Prev
    Next
    INDEX
    Explanations

    strongly emphasized nouns or phrases related to significant concepts and themes

    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
    ghed
    -0.49
     su
    -0.46
     suh
    -0.45
    none
    -0.43
     none
    -0.42
    aband
    -0.41
    ieval
    -0.40
    eriam
    -0.40
    ]++;
    -0.40
     Fakult
    -0.40
    POSITIVE LOGITS
    rungsseite
    0.99
    Geplaatst
    0.92
    Datuak
    0.84
    তথ্যসূত্র
    0.82
    ########.
    0.79
     Мексичка
    0.78
     autorytatywna
    0.75
     ContentValues
    0.75
    LookAnd
    0.74
     defaultstate
    0.74
    Activations Density 0.015%

    No Known Activations