© 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. 43865
    Prev
    Next
    INDEX
    Explanations

    properties

    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
    pure
    -1.09
    Pure
    -1.00
    Personendaten
    -0.98
    PURE
    -0.94
     pure
    -0.88
    inher
    -0.85
     Pure
    -0.81
     itſelf
    -0.79
     PURE
    -0.78
     pura
    -0.77
    POSITIVE LOGITS
     in
    0.53
     of
    0.52
     des
    0.48
     electronic
    0.47
    ,
    0.46
     molecular
    0.45
     de
    0.45
     at
    0.44
    ή
    0.43
     a
    0.42
    Activations Density 0.101%

    No Known Activations