© 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. 4-CLT-HP
    4. 3084
    Prev
    Next
    INDEX
    Explanations

    about

    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
     NSCoder
    -0.90
     tartalomajánló
    -0.67
    ConstraintMaker
    -0.65
    mobileqq
    -0.65
     getopt
    -0.64
     comerciais
    -0.63
     történ
    -0.60
    SequentialGroup
    -0.60
     aveug
    -0.59
     tendenza
    -0.58
    POSITIVE LOGITS
    TagMode
    0.54
     reflecting
    0.51
     using
    0.49
    Clik
    0.49
     pushing
    0.49
     preparing
    0.48
     providing
    0.48
     making
    0.48
    ‚¬
    0.47
    });*/
    0.47
    Activations Density 0.001%

    No Known Activations