© 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. 5-CLT-HP
    7. 98062
    Prev
    Next
    INDEX
    Explanations

    in

    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
    RegistryLite
    -0.64
    helves
    -0.58
    archiviato
    -0.57
    OGND
    -0.52
    ParallelGroup
    -0.52
     nonUne
    -0.51
    rungsseite
    -0.50
    protoimpl
    -0.50
    Bronnen
    -0.49
    écoute
    -0.49
    POSITIVE LOGITS
     pinulongan
    0.71
     ways
    0.68
    <bos>
    0.68
     return
    0.65
     anyway
    0.61
    return
    0.60
     صوتيه
    0.59
     WAYS
    0.56
    resave
    0.52
    anyway
    0.51
    Activations Density 0.002%

    No Known Activations