© 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. 98046
    Prev
    Next
    INDEX
    Explanations

    bit

    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
    principalColumn
    -0.79
     يتيمه
    -0.76
    ousands
    -0.74
    DebuggerNonUser
    -0.71
     referenties
    -0.70
    ChildScrollView
    -0.69
     onAnimation
    -0.68
    KURZBESCHREIBUNG
    -0.68
     ujednoznacz
    -0.65
     ContentValues
    -0.64
    POSITIVE LOGITS
    le
    0.44
    v
    0.44
    olar
    0.40
     gestão
    0.39
    ছে
    0.39
    Build
    0.39
    Obs
    0.39
    om
    0.39
    ingar
    0.38
    omor
    0.38
    Activations Density 0.000%

    No Known Activations