© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21615
    Prev
    Next
    INDEX
    Explanations

    concepts related to genetic modifications and mutations

    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
    出版年
    -0.61
     reichen
    -0.52
    võ
    -0.52
     Destin
    -0.49
    annique
    -0.47
    rentina
    -0.46
     vouch
    -0.46
    ρκ
    -0.45
    Elect
    -0.45
     diplomatic
    -0.45
    POSITIVE LOGITS
    省市镇
    0.70
    millimeters
    0.64
    PYX
    0.59
    CloseOperation
    0.57
    SuppressLint
    0.57
    ]")]
    0.57
    Sklici
    0.57
    DropColumn
    0.57
    lobo
    0.57
    obt
    0.56
    Activations Density 0.017%

    No Known Activations