Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74584
    Prev
    Next
    INDEX
    Explanations

    k

    np_max-act-logits · 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
    PerformLayout
    -0.76
    AndEndTag
    -0.73
    BrowserModule
    -0.71
     ciga
    -0.65
     Reſ
    -0.63
     ***!
    -0.63
    +#+#
    -0.63
     propOrder
    -0.61
    InjectAttribute
    -0.60
     GenerationType
    -0.60
    POSITIVE LOGITS
    ichord
    0.45
    isan
    0.44
    elson
    0.42
    ########.
    0.42
    ari
    0.40
    illado
    0.40
    yeong
    0.40
    zí
    0.40
     TextAppearance
    0.40
    aru
    0.39
    Activations Density 0.001%

    No Known Activations