© 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. 96836
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     Yourself
    -0.44
    enumii
    -0.44
    enumi
    -0.42
    lith
    -0.42
     Yet
    -0.41
    luck
    -0.40
    glob
    -0.40
     nas
    -0.40
    /@
    -0.40
    ret
    -0.40
    POSITIVE LOGITS
     tartalomajánló
    0.85
     contextLoads
    0.85
    DockStyle
    0.67
     initComponents
    0.63
     AssemblyVersion
    0.61
    OrBuilder
    0.59
     Wikimedijinoj
    0.59
    WriteBarrier
    0.58
    DebuggerNonUser
    0.57
     Audiodateien
    0.57
    Activations Density 0.710%

    No Known Activations