© 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. 11072
    Prev
    Next
    INDEX
    Explanations

    references to storytelling and nostalgia

    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
     NSCoder
    -0.85
    NOPQRST
    -0.83
    expandindo
    -0.77
    ArgsConstructor
    -0.75
    Abitanti
    -0.74
    kfree
    -0.72
     onPostExecute
    -0.71
    Portail
    -0.71
    astéroïdes
    -0.71
    #+#
    -0.70
    POSITIVE LOGITS
     Meanwhile
    0.55
    Meanwhile
    0.49
     meanwhile
    0.47
    <bos>
    0.47
    (
    0.46
    @
    0.45
    ase
    0.44
    dia
    0.42
     (
    0.41
    -
    0.40
    Activations Density 0.191%

    No Known Activations