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. 20273
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "the License" and references to compliance with it

    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
    LICENSE
    -1.34
    )))));
    -0.59
     kasarigan
    -0.58
    ISupport
    -0.56
    })`
    -0.55
     BoxFit
    -0.53
    })}$
    -0.51
    Baca
    -0.50
    HasIndex
    -0.48
    amur
    -0.48
    POSITIVE LOGITS
     TestBed
    0.65
     maxn
    0.61
    towanie
    0.59
    Зноскі
    0.57
     ioutil
    0.56
    Приятного
    0.56
     yourselves
    0.56
    PhysRevD
    0.56
     polaire
    0.54
     actionMode
    0.54
    Activations Density 0.000%

    No Known Activations