© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94705
    Prev
    Next
    INDEX
    Explanations

    Technical writing with symbols

    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
    RenderAtEndOf
    -0.95
    LookAnd
    -0.61
     InputDecoration
    -0.58
    AppMethodBeat
    -0.57
    SaveVideo
    -0.54
    asiun
    -0.53
    %;">
    -0.53
    SizeMode
    -0.51
    TagMode
    -0.50
    }]
    -0.50
    POSITIVE LOGITS
    KommentareTeilen
    0.55
    ATF
    0.54
     optimally
    0.53
     tepat
    0.49
     uplifted
    0.47
    EDEFAULT
    0.47
     optimal
    0.47
    Aiheesta
    0.47
     better
    0.46
    kaner
    0.46
    Activations Density 0.005%

    No Known Activations