© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93028
    Prev
    Next
    INDEX
    Explanations

    box

    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
    awtextra
    -0.92
    ंदीखरीदारी
    -0.82
     Normdatei
    -0.81
     AssemblyCulture
    -0.81
    SequentialGroup
    -0.81
    Vidite
    -0.80
    UnsafeEnabled
    -0.74
     définiti
    -0.74
     devenus
    -0.74
    <bos>
    -0.73
    POSITIVE LOGITS
     drain
    0.48
     nobody
    0.44
    .
    0.41
     or
    0.41
     drains
    0.40
     "
    0.40
     winch
    0.40
     katal
    0.40
     and
    0.40
    mayer
    0.39
    Activations Density 0.071%

    No Known Activations