© 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. 92123
    Prev
    Next
    INDEX
    Explanations

    improvements

    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
    Hochspringen
    -0.63
    EndInit
    -0.63
    InjectMocks
    -0.60
    IntoConstraints
    -0.56
     LUMP
    -0.54
     سكانية
    -0.53
     насеље
    -0.53
    Conservative
    -0.52
    annica
    -0.51
    ArgsConstructor
    -0.50
    POSITIVE LOGITS
     texture
    0.53
    Дереккөздер
    0.51
     poor
    0.50
     circulation
    0.49
    idopsis
    0.47
     resistance
    0.46
     solubility
    0.45
     posture
    0.44
     permeability
    0.44
     NUKAT
    0.44
    Activations Density 0.005%

    No Known Activations