© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2520
    Prev
    Next
    INDEX
    Explanations

    interviews

    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
    __((
    -0.59
    (&:
    -0.48
    CardModule
    -0.45
    clerview
    -0.45
     NgModule
    -0.44
    šķ
    -0.43
    大さじ
    -0.42
    到底
    -0.39
     sight
    -0.39
     χει
    -0.39
    POSITIVE LOGITS
     with
    1.17
    bootstrapcdn
    0.80
     avec
    0.80
    With
    0.74
    with
    0.72
     kanssa
    0.72
     dengan
    0.71
     With
    0.71
     WITH
    0.71
    avec
    0.69
    Activations Density 0.005%

    No Known Activations