© 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. 92555
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings/fragments

    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
    ьаж
    -0.86
     CreateTagHelper
    -0.84
    SharedDtor
    -0.83
     Italijani
    -0.81
     distanciation
    -0.78
    存于互联网档案馆
    -0.78
     Forumite
    -0.76
     насељу
    -0.73
    .*")]
    -0.73
    хьтан
    -0.72
    POSITIVE LOGITS
     so
    0.54
     get
    0.43
     think
    0.42
    τσι
    0.40
    AN
    0.39
    So
    0.37
    Y
    0.36
     feel
    0.36
     
    0.35
    <sup>
    0.35
    Activations Density 0.000%

    No Known Activations