Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 14820
    Prev
    Next
    INDEX
    Explanations

    instances of the word "generalize" and its variations, indicating a focus on the concept of generalization 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
    حياته
    -0.66
    NewUrlParser
    -0.60
    xtype
    -0.58
     externes
    -0.57
    lesia
    -0.57
    DCE
    -0.57
     Cx
    -0.56
    setParameter
    -0.55
    pex
    -0.55
    يين
    -0.55
    POSITIVE LOGITS
    ArgsConstructor
    0.63
    MarshalTo
    0.62
     masculinos
    0.60
     rús
    0.59
    OGND
    0.58
    ReusableCell
    0.57
    WithMany
    0.56
     térm
    0.55
     estekak
    0.55
    randomUUID
    0.54
    Activations Density 0.027%

    No Known Activations