© 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. 2819
    Prev
    Next
    INDEX
    Explanations

    time

    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
     stok
    -0.37
     line
    -0.36
     inter
    -0.35
    etsk
    -0.33
    line
    -0.33
    ITH
    -0.33
    NameValuePair
    -0.32
    }}_
    -0.32
     sort
    -0.32
    ith
    -0.31
    POSITIVE LOGITS
     AssemblyCulture
    0.90
    AndEndTag
    0.87
    AutoScaleMode
    0.87
    InputBorder
    0.82
     '\\;'
    0.81
     Савезне
    0.81
    ImageContext
    0.77
     pétrole
    0.76
     publicitaires
    0.76
    كتشاف
    0.75
    Activations Density 0.003%

    No Known Activations