© 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. 1040
    Prev
    Next
    INDEX
    Explanations

    code licenses and disclaimers, in particular the phrase "AS IS."

    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
    rrggbb
    -0.63
    tableFuture
    -0.59
     '\\;'
    -0.59
     typelib
    -0.55
     linkovi
    -0.54
    RectangleBorder
    -0.52
    ocz
    -0.51
    WebControls
    -0.51
     виправивши
    -0.50
    TargetException
    -0.50
    POSITIVE LOGITS
     Is
    2.42
    Is
    2.31
     IS
    2.13
     is
    1.97
    is
    1.96
    IS
    1.72
     getIs
    1.58
     Iso
    1.41
    getIs
    1.36
     İs
    1.31
    Activations Density 1.129%

    No Known Activations