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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43780
    Prev
    Next
    INDEX
    Explanations

    praise

    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
     praises
    -0.88
     praise
    -0.86
     references
    -0.85
     allusions
    -0.78
     Mention
    -0.77
     compliments
    -0.75
     emphasis
    -0.68
     mentions
    -0.68
     Praise
    -0.68
     praising
    -0.68
    POSITIVE LOGITS
     MonoBehaviour
    0.61
    ReusableCell
    0.59
     onCreateView
    0.58
    stdc
    0.57
    ioutil
    0.56
    SceneManagement
    0.56
    \"]
    0.54
     TMPro
    0.54
    tagena
    0.54
     мәкалә
    0.53
    Activations Density 0.065%

    No Known Activations