© 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. 5-CLT-HP
    7. 93365
    Prev
    Next
    INDEX
    Explanations

    Pakistan

    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
     PLWABN
    -0.56
     createSlice
    -0.54
    ational
    -0.52
    erà
    -0.52
    IZZ
    -0.51
    ीय
    -0.50
    IUS
    -0.50
    ato
    -0.49
    zong
    -0.49
    avy
    -0.49
    POSITIVE LOGITS
    InjectMocks
    0.50
    uttosto
    0.50
    blasts
    0.48
     encantan
    0.47
    tanleria
    0.47
     fathoms
    0.47
    numerusform
    0.46
    MLLoader
    0.46
    LEncoder
    0.45
     autorytatywna
    0.45
    Activations Density 0.002%

    No Known Activations