© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 2379
    Prev
    Next
    INDEX
    Explanations

    positive film reviews

    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
    expandindo
    -0.71
     виправивши
    -0.67
    Aiheesta
    -0.59
     antigüedad
    -0.52
    IntoConstraints
    -0.51
     تعريف
    -0.50
     naturale
    -0.50
     naturais
    -0.49
    interopRequire
    -0.49
    CMAKE
    -0.47
    POSITIVE LOGITS
     reviewer
    0.89
     reviewers
    0.80
     rating
    0.76
    Critic
    0.69
     critic
    0.69
     Reviewer
    0.67
     Rating
    0.66
     AllMusic
    0.65
     RATING
    0.65
     AssemblyCulture
    0.64
    Activations Density 0.103%

    No Known Activations