© 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. 24-RES-MATRYOSHKA-DC
    7. 53
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to historical and political events

    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.24.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.24.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
    JNIEnv
    -0.75
    written
    -0.69
    ]")]
    -0.69
    InputBorder
    -0.68
     auffi
    -0.67
    '},
    -0.66
    ActiveRecord
    -0.66
    ]='\
    -0.66
    %"),
    -0.65
     faſt
    -0.65
    POSITIVE LOGITS
     was
    2.36
     had
    1.79
     did
    1.63
     gave
    1.49
     took
    1.48
     went
    1.45
     were
    1.45
     showed
    1.45
     seemed
    1.45
     appeared
    1.44
    Activations Density 5.695%

    No Known Activations