© 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. 310
    Prev
    Next
    INDEX
    Explanations

    phrases indicating originality or uniqueness in a collection of works

    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
     logarithms
    -0.43
    셨
    -0.43
    сии
    -0.42
     pasteur
    -0.41
    Benzene
    -0.40
    Mascul
    -0.40
     ainsi
    -0.40
     vostre
    -0.40
    ינו
    -0.39
    Avant
    -0.39
    POSITIVE LOGITS
     consultato
    0.84
     autorytatywna
    0.84
    ScopeManager
    0.80
    enderror
    0.74
     برانيه
    0.73
    PYX
    0.73
    LookAnd
    0.72
     Wicidata
    0.71
    AnchorStyles
    0.71
    ⓧ
    0.71
    Activations Density 4.086%

    No Known Activations