© 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. 1-CLT-HP
    7. 12328
    Prev
    Next
    INDEX
    Explanations

    ška

    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
     adipis
    -0.46
    man
    -0.45
    der
    -0.44
    UIControlState
    -0.43
    dataclass
    -0.43
    r
    -0.42
    ter
    -0.42
     hashlib
    -0.40
    лич
    -0.39
     Méri
    -0.39
    POSITIVE LOGITS
     lisäksi
    0.79
    MessageTagHelper
    0.77
    دانشنامهٔ
    0.76
     complètes
    0.74
     varandra
    0.73
     jotka
    0.72
    Excerpts
    0.71
     BrowserModule
    0.71
     mukana
    0.69
    Tikang
    0.68
    Activations Density 0.078%

    No Known Activations