© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4299
    Prev
    Next
    INDEX
    Explanations

    licenses or management

    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
    __(/*!
    -0.65
    sidemargin
    -0.62
    Xna
    -0.60
    Personensuche
    -0.60
    permitAll
    -0.59
     esternos
    -0.59
    WriteTagHelper
    -0.59
     nakalista
    -0.58
    AddTagHelper
    -0.57
    olum
    -0.57
    POSITIVE LOGITS
    abel
    0.46
    کتری
    0.44
    toCharArray
    0.44
     dibawa
    0.42
    ベル
    0.41
     portefeuille
    0.41
    брати
    0.41
    CPE
    0.40
    pted
    0.40
     cielos
    0.40
    Activations Density 0.005%

    No Known Activations