© 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. 97058
    Prev
    Next
    INDEX
    Explanations

    from

    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
     from
    -1.66
    from
    -1.55
     från
    -1.28
    From
    -1.21
     ifrån
    -1.11
    จาก
    -1.09
     FROM
    -1.04
     From
    -1.03
     kutoka
    -1.01
     vanuit
    -0.96
    POSITIVE LOGITS
     the
    1.33
     a
    1.07
     an
    0.96
     their
    0.88
     any
    0.77
     what
    0.75
     certain
    0.74
     these
    0.71
     its
    0.69
     this
    0.67
    Activations Density 0.309%

    No Known Activations