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. 73837
    Prev
    Next
    INDEX
    Explanations

    technical options

    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
    C
    -0.59
    b
    -0.57
     ac
    -0.54
    c
    -0.54
    dm
    -0.52
    AIC
    -0.51
    A
    -0.51
    AID
    -0.50
    psack
    -0.50
    cba
    -0.50
    POSITIVE LOGITS
    errHandler
    0.64
     E
    0.64
     CreateTagHelper
    0.56
     Normdatei
    0.54
    setVerticalGroup
    0.52
    ⓧ
    0.52
     F
    0.51
    #+#
    0.50
    UnknownFieldSet
    0.50
     Elixir
    0.49
    Activations Density 0.003%

    No Known Activations