© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4571
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Havolalar
    -0.51
     từng
    -0.50
    Véxase
    -0.49
    '],
    -0.48
     each
    -0.47
    ]=="
    -0.47
    '),
    -0.45
    AZINE
    -0.45
     solved
    -0.44
    ]!='
    -0.44
    POSITIVE LOGITS
    SharedDtor
    0.67
    Autoritní
    0.65
     InputDecoration
    0.60
     '\\;'
    0.60
    UrlResolution
    0.59
    WebVitals
    0.57
    OGND
    0.56
    ագրություններ
    0.56
     Normdatei
    0.56
    protoimpl
    0.56
    Activations Density 0.002%

    No Known Activations