© 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. 22-RES-MATRYOSHKA-DC
    7. 2286
    Prev
    Next
    INDEX
    Explanations

    the word "broad" and words related to its various meanings

    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.22.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.22.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
     pulumi
    -0.76
    tagHelperRunner
    -0.73
     GenerationType
    -0.72
     idolatry
    -0.67
    jednoc
    -0.67
    netbeans
    -0.66
    yntaxException
    -0.65
     JpaRepository
    -0.65
     spinners
    -0.64
    LoadScene
    -0.63
    POSITIVE LOGITS
    casted
    0.84
    spectrum
    0.66
     spectrum
    0.66
    minded
    0.58
    casting
    0.58
     Based
    0.57
    sword
    0.56
     based
    0.54
    caster
    0.54
    Based
    0.53
    Activations Density 0.029%

    No Known Activations