© 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. 97698
    Prev
    Next
    INDEX
    Explanations

    directions

    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
     autorytatywna
    -0.56
     utafitiHapana
    -0.54
     stampa
    -0.50
     متعلقه
    -0.49
     kasarigan
    -0.48
    Дереккөздер
    -0.47
     ligiloj
    -0.47
    >{@
    -0.47
    Ingredienti
    -0.46
    #+#
    -0.45
    POSITIVE LOGITS
    .
    0.81
    Tikang
    0.59
    ims
    0.55
    encing
    0.54
    ikai
    0.53
    sie
    0.52
    ikou
    0.51
    dur
    0.50
    arie
    0.50
    ignty
    0.49
    Activations Density 0.008%

    No Known Activations