© 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
    2. Gemma-2-2B
    3. 18-RES-MATRYOSHKA-DC
    4. 1035
    Prev
    Next
    INDEX
    Explanations

    hyphens in filenames and code or identifiers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    Hrsg
    -0.58
    .
    -0.56
     /*
    -0.53
    ,
    -0.52
    ークル
    -0.52
    ündigung
    -0.51
    었습니다
    -0.51
    жки
    -0.51
     знаем
    -0.50
    ?
    -0.50
    POSITIVE LOGITS
    *-*-
    1.17
    *-
    1.12
    &-
    1.08
    ®-
    1.02
     }}-
    1.01
    »-
    0.98
    '-
    0.98
    -​
    0.94
    ()-
    0.93
    =-=-=-=-
    0.92
    Activations Density 0.848%

    No Known Activations