© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41215
    Prev
    Next
    INDEX
    Explanations

    overworked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.89
    tanleria
    -0.88
     NgModule
    -0.82
    berdayakan
    -0.80
    ьаж
    -0.75
    省市镇
    -0.75
    DIPSETTING
    -0.73
     Lode
    -0.71
    AddTagHelper
    -0.71
    UnsafeEnabled
    -0.71
    POSITIVE LOGITS
    ly
    0.51
    ten
    0.48
    $};
    0.47
    st
    0.47
     mass
    0.47
     "":
    0.47
     mặt
    0.46
    ']):
    0.45
    \"");
    0.44
    ))$.
    0.44
    Activations Density 1.589%

    No Known Activations