© 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. 0-CLT-HP
    4. 40352
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
    ication
    -1.41
    ications
    -1.19
    icate
    -1.15
    icating
    -0.96
     ſtate
    -0.95
    gee
    -0.91
     protocols
    -0.91
    icated
    -0.89
     purpoſe
    -0.88
     laſt
    -0.85
    POSITIVE LOGITS
    pl
    0.49
     The
    0.47
     That
    0.47
    '
    0.47
     Your
    0.44
     It
    0.44
    the
    0.44
    The
    0.44
    por
    0.43
    ’
    0.43
    Activations Density 0.021%

    No Known Activations