© 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. 1021
    Prev
    Next
    INDEX
    Explanations

    strings "sh", "uc", "wh", "noh", and similar short strings of letters

    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
    able
    -1.01
    ability
    -0.84
    i
    -0.76
    ages
    -0.73
    e
    -0.73
    ado
    -0.71
    away
    -0.71
    age
    -0.71
    azione
    -0.69
    ed
    -0.69
    POSITIVE LOGITS
    hhhh
    0.66
    hhh
    0.65
    hhhhhhhh
    0.64
    hhhhh
    0.63
    s
    0.60
    hh
    0.55
    sdk
    0.42
    sj
    0.41
    sides
    0.41
    sth
    0.40
    Activations Density 0.567%

    No Known Activations