© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94078
    Prev
    Next
    INDEX
    Explanations

    āh

    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
    __*/
    -0.77
     Jego
    -0.65
     Offisielt
    -0.57
    enderror
    -0.55
     ostavi
    -0.52
    webElement
    -0.52
     BufferedWriter
    -0.52
    BIOGRAPHY
    -0.51
    praš
    -0.50
     coloro
    -0.49
    POSITIVE LOGITS
    InjectAttribute
    0.59
    IsMutable
    0.54
     sih
    0.50
    +#+#
    0.46
    Alike
    0.46
     uintptr
    0.45
     NUKAT
    0.45
    Quoi
    0.45
    providedIn
    0.44
     Has
    0.44
    Activations Density 0.014%

    No Known Activations