© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 93965
    Prev
    Next
    INDEX
    Explanations

    specifically

    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
     senare
    -0.43
     citada
    -0.39
     etc
    -0.39
    offered
    -0.38
     bestuur
    -0.37
     offered
    -0.37
     églises
    -0.37
    ഈ
    -0.37
    bollah
    -0.36
     and
    -0.36
    POSITIVE LOGITS
    tagHelperRunner
    0.90
     Roskov
    0.81
    EndInit
    0.78
    numerusform
    0.77
     "..\..\..\
    0.75
    +#+
    0.75
    EDEFAULT
    0.71
    ########.
    0.70
    abestanden
    0.69
     متعلقه
    0.69
    Activations Density 0.002%

    No Known Activations