© 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. 5771
    Prev
    Next
    INDEX
    Explanations

    terms related to medical evaluations and outcomes

    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
     dé
    -0.43
     матери
    -0.43
    lock
    -0.43
    <sup>
    -0.42
    inação
    -0.42
    DateTimeField
    -0.41
    ）；
    -0.40
    }$;
    -0.40
    ]))
    -0.39
    RTEE
    -0.39
    POSITIVE LOGITS
    bcryptjs
    0.93
    новништво
    0.84
    providedIn
    0.77
    WebElementEntity
    0.73
    SBATCH
    0.71
     heapq
    0.70
    enumi
    0.68
    jface
    0.68
     rospy
    0.67
    __":
    0.65
    Activations Density 0.655%

    No Known Activations