© 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. 91721
    Prev
    Next
    INDEX
    Explanations

    Directional prepositions

    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
     zvlá
    -0.47
     descre
    -0.47
     Aufs
    -0.46
    maketitle
    -0.44
     出版
    -0.43
    Reprints
    -0.42
    Doctoral
    -0.41
    テーション
    -0.41
    ########.
    -0.40
    """.
    -0.40
    POSITIVE LOGITS
     FetchType
    0.96
    mybatisplus
    0.92
     themselves
    0.85
    themselves
    0.81
    RenderAtEndOf
    0.76
    GenerationType
    0.74
    ReusableCell
    0.71
     autorytatywna
    0.69
    :✨
    0.68
     CascadeType
    0.68
    Activations Density 0.001%

    No Known Activations