© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16167
    Prev
    Next
    INDEX
    Explanations

    Hager

    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
    Negative Logits
    TemporalType
    -0.52
    ahrt
    -0.50
    ismet
    -0.47
    RegistryLite
    -0.47
    ClCompile
    -0.46
    lect
    -0.45
    രു
    -0.45
     dat
    -0.45
     unknownFields
    -0.44
    Fon
    -0.43
    POSITIVE LOGITS
     surla
    0.67
    Hentet
    0.61
    ")));
    0.56
    jiri
    0.52
    ]}>
    0.50
    }}/>
    0.50
    TagHelpers
    0.50
    principalColumn
    0.49
    typeorm
    0.49
     cedera
    0.49
    Activations Density 0.021%

    No Known Activations