© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44206
    Prev
    Next
    INDEX
    Explanations

    reys

    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
     autorytatywna
    -0.87
    reys
    -0.87
    ConstraintMaker
    -0.83
    ioutil
    -0.79
    — 
    -0.77
    StoryboardSegue
    -0.75
    erequisites
    -0.75
    曖昧さ回避
    -0.75
     Савезне
    -0.73
    weed
    -0.72
    POSITIVE LOGITS
    N
    0.58
    of
    0.57
    //
    0.57
     fairies
    0.51
    #
    0.50
    to
    0.50
     rooster
    0.50
    gin
    0.50
    http
    0.50
    if
    0.49
    Activations Density 1.627%

    No Known Activations