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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92593
    Prev
    Next
    INDEX
    Explanations

    importance

    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
    IUrlHelper
    -0.52
     Barlow
    -0.48
    ignées
    -0.46
    ntag
    -0.46
    fjspx
    -0.44
    ujan
    -0.44
    Autoritní
    -0.43
     fanfare
    -0.43
     stage
    -0.42
    MethodType
    -0.42
    POSITIVE LOGITS
    tvguidetime
    0.64
     vérit
    0.64
    SpringBootTest
    0.64
    ]")]
    0.63
     morire
    0.61
    saraba
    0.57
    VIAF
    0.56
     öppna
    0.56
     houſe
    0.55
     Houſe
    0.55
    Activations Density 0.000%

    No Known Activations