© 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. 16627
    Prev
    Next
    INDEX
    Explanations

    terms related to modeling and representation in various contexts

    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
    ab
    -0.46
     jal
    -0.44
     <<<<<<<<<<<<<<
    -0.44
    avad
    -0.44
    яр
    -0.44
    esm
    -0.44
    psz
    -0.44
    labelControl
    -0.44
     Cir
    -0.43
    неопр
    -0.43
    POSITIVE LOGITS
    verwijspagina
    0.76
    FieldBuilder
    0.74
     ArrayAdapter
    0.73
     peindre
    0.72
    醐
    0.71
     vectorielle
    0.70
     depicted
    0.70
    tagHelperRunner
    0.69
    AnchorStyles
    0.68
    Дереккөздер
    0.67
    Activations Density 0.258%

    No Known Activations